This document summarizes a paper that presents excerpts from Ghana's Citizenship Act formalized as a logic theorem. The paper aims to analyze the semantics of the legal text by formalizing it in logic. It discusses challenges with ambiguity in legal language and how formalization can help reveal semantic implications. It presents the Citizenship Act formalized with logical connectives and analyzes how this preserves clarity and allows for deductive reasoning through the text. The formalization is said to establish the intended semantics while preventing wrong meanings from ambiguity.
CITIZENSHIP ACT (591) OF GHANA AS A LOGIC THEOREM AND ITS SEMANTIC IMPLICATIONSijnlc
This paper presents excerpts of the natural text of the Citizenship Act of the Republic of Ghana, ACT 2000 (591), as a logic theorem in First Order Logic (FOL) language. The formalism of this piece of law is done to allow for semantic analysis of the text by machines. The results of this research also deals with the problem of ambiguities in the legal text, andreveals the semantic consequence of the natural construction or textual structure of the piece of law;one major problem ofthe semantics of legal text has been the problem of ambiguities, which largely affects interpretations that are alluded to legal statements. Some constructed sentences sometimesdo not reflect the semantic intentions of the composers of the sentences, due to inherent ambiguities or technical faults in the structure of some parts of the statements.The formalism of the Actin this paper provides logical proofs and deductions which are asserted to establish clarity and to reveal semantic errors, or otherwise preserve the semantic intentions of the Act
An Intersemiotic Translation of Normative Utterances to Machine Languagedannyijwest
Programming Languages (PL) effectively performs an intersemiotic translation from a natural language to
machine language. PL comprises a set of instructions to implement algorithms, i.e., to perform
(computational) tasks. Similarly to Normative Languages (NoL), PLs are formal languages that can
perform both regulative and constitutive functions. The paper presents the first results of interdisciplinary
research aimed at highlighting the similarities between NoL (social sciences) and PL (computer science)
through everyday life examples, exploiting Object-Oriented Programming Language tools and an Internet
of Things (IoT) system as a case study. Given the pandemic emergency, the urge to move part of our social
life to the digital world arose, together with the need to effectively transpose regulative rules and
constitutive rules through different strategies for translating a normative utterance expressed in natural
language.
INDONESIAN-ENGLISH CROSS-LINGUAL LEGAL ONTOLOGY FOR INFORMATION RETRIEVALdannyijwest
This research encompasses the construction of a multilingual lexical database for cross-lingual
information retrieval in the Indonesian legal domain. Multilingual lexical database featuring lexically
and legally grounded conceptual representation can fit the cross-lingual information retrieval. Lexical
database use Ontology Web Language (OWL) representation language. This representation is useful to provide application developers a high-quality resource and to promote interoperability.
Ali Akbar Dehkhoda, the prominent lexicographer, describes a person who has difficulty in grasping knowledge as someone who “Cannot understand something without knowing all its details.” If the knowledge required by somebody is in a language other than the person’s mother tongue, access to this knowledge will surely meet special difficulties resulting from the person’s lack of mastery over the second
language. Any project that can monitor knowledge sources written in English and change them into the
user’s language by employing a simple understandable model is capable of being a knowledge-based
project with a world view regarding text simplification. This article creates a knowledge system,
investigates some algorithms for analyzing contents of complex texts, and presents solutions for changing
such texts simple and understandable ones. Texts are automatically analyzed and their ambiguous points
are identified by software, but it is the author or the human agent who makes decisions concerning
omission of the ambiguities or correction of the texts.
Robust extended tokenization framework for romanian by semantic parallel text...ijnlc
Tokenization is considered a solved problem when reduced to just word borders identification, punctuation
and white spaces handling. Obtaining a high quality outcome from this process is essential for subsequent
NLP piped processes (POS-tagging, WSD). In this paper we claim that to obtain this quality we need to use
in the tokenization disambiguation process all linguistic, morphosyntactic, and semantic-level word-related
information as necessary. We also claim that semantic disambiguation performs much better in a bilingual
context than in a monolingual one. Then we prove that for the disambiguation purposes the bilingual text
provided by high profile on-line machine translation services performs almost to the same level with
human-originated parallel texts (Gold standard). Finally we claim that the tokenization algorithm
incorporated in TORO can be used as a criterion for on-line machine translation services comparative
quality assessment and we provide a setup for this purpose.
A SURVEY OF GRAMMAR CHECKERS FOR NATURAL LANGUAGEScsandit
ABSTRACT
Natural Language processing is an interdisciplinary branch of linguistic and computer science studied under the Artificial Intelligence (AI) that gave birth to an allied area called
‘Computational Linguistic’ which focuses on processing of natural languages on computational devices. A natural language consists of a large number of sentences which are linguistic units involving one or more words linked together in accordance with a set of predefined rules called grammar. Grammar checking is the task of validating sentences syntactically and is a prominent tool within language engineering. Our review draws on the recent development of various grammar checkers to look at past, present and the future in a new light. Our review covers grammar checkers of many languages with the aim of seeking their approaches, methodologies for developing new tool and system as a whole. The survey concludes with the discussion of various features included in existing grammar checkers of foreign languages as well as a few Indian Languages.
CITIZENSHIP ACT (591) OF GHANA AS A LOGIC THEOREM AND ITS SEMANTIC IMPLICATIONSijnlc
This paper presents excerpts of the natural text of the Citizenship Act of the Republic of Ghana, ACT 2000 (591), as a logic theorem in First Order Logic (FOL) language. The formalism of this piece of law is done to allow for semantic analysis of the text by machines. The results of this research also deals with the problem of ambiguities in the legal text, andreveals the semantic consequence of the natural construction or textual structure of the piece of law;one major problem ofthe semantics of legal text has been the problem of ambiguities, which largely affects interpretations that are alluded to legal statements. Some constructed sentences sometimesdo not reflect the semantic intentions of the composers of the sentences, due to inherent ambiguities or technical faults in the structure of some parts of the statements.The formalism of the Actin this paper provides logical proofs and deductions which are asserted to establish clarity and to reveal semantic errors, or otherwise preserve the semantic intentions of the Act
An Intersemiotic Translation of Normative Utterances to Machine Languagedannyijwest
Programming Languages (PL) effectively performs an intersemiotic translation from a natural language to
machine language. PL comprises a set of instructions to implement algorithms, i.e., to perform
(computational) tasks. Similarly to Normative Languages (NoL), PLs are formal languages that can
perform both regulative and constitutive functions. The paper presents the first results of interdisciplinary
research aimed at highlighting the similarities between NoL (social sciences) and PL (computer science)
through everyday life examples, exploiting Object-Oriented Programming Language tools and an Internet
of Things (IoT) system as a case study. Given the pandemic emergency, the urge to move part of our social
life to the digital world arose, together with the need to effectively transpose regulative rules and
constitutive rules through different strategies for translating a normative utterance expressed in natural
language.
INDONESIAN-ENGLISH CROSS-LINGUAL LEGAL ONTOLOGY FOR INFORMATION RETRIEVALdannyijwest
This research encompasses the construction of a multilingual lexical database for cross-lingual
information retrieval in the Indonesian legal domain. Multilingual lexical database featuring lexically
and legally grounded conceptual representation can fit the cross-lingual information retrieval. Lexical
database use Ontology Web Language (OWL) representation language. This representation is useful to provide application developers a high-quality resource and to promote interoperability.
Ali Akbar Dehkhoda, the prominent lexicographer, describes a person who has difficulty in grasping knowledge as someone who “Cannot understand something without knowing all its details.” If the knowledge required by somebody is in a language other than the person’s mother tongue, access to this knowledge will surely meet special difficulties resulting from the person’s lack of mastery over the second
language. Any project that can monitor knowledge sources written in English and change them into the
user’s language by employing a simple understandable model is capable of being a knowledge-based
project with a world view regarding text simplification. This article creates a knowledge system,
investigates some algorithms for analyzing contents of complex texts, and presents solutions for changing
such texts simple and understandable ones. Texts are automatically analyzed and their ambiguous points
are identified by software, but it is the author or the human agent who makes decisions concerning
omission of the ambiguities or correction of the texts.
Robust extended tokenization framework for romanian by semantic parallel text...ijnlc
Tokenization is considered a solved problem when reduced to just word borders identification, punctuation
and white spaces handling. Obtaining a high quality outcome from this process is essential for subsequent
NLP piped processes (POS-tagging, WSD). In this paper we claim that to obtain this quality we need to use
in the tokenization disambiguation process all linguistic, morphosyntactic, and semantic-level word-related
information as necessary. We also claim that semantic disambiguation performs much better in a bilingual
context than in a monolingual one. Then we prove that for the disambiguation purposes the bilingual text
provided by high profile on-line machine translation services performs almost to the same level with
human-originated parallel texts (Gold standard). Finally we claim that the tokenization algorithm
incorporated in TORO can be used as a criterion for on-line machine translation services comparative
quality assessment and we provide a setup for this purpose.
A SURVEY OF GRAMMAR CHECKERS FOR NATURAL LANGUAGEScsandit
ABSTRACT
Natural Language processing is an interdisciplinary branch of linguistic and computer science studied under the Artificial Intelligence (AI) that gave birth to an allied area called
‘Computational Linguistic’ which focuses on processing of natural languages on computational devices. A natural language consists of a large number of sentences which are linguistic units involving one or more words linked together in accordance with a set of predefined rules called grammar. Grammar checking is the task of validating sentences syntactically and is a prominent tool within language engineering. Our review draws on the recent development of various grammar checkers to look at past, present and the future in a new light. Our review covers grammar checkers of many languages with the aim of seeking their approaches, methodologies for developing new tool and system as a whole. The survey concludes with the discussion of various features included in existing grammar checkers of foreign languages as well as a few Indian Languages.
BIDIRECTIONAL MACHINE TRANSLATION BETWEEN TURKISH AND TURKISH SIGN LANGUAGE: ...ijnlc
Communication is one of the first necessities for human beings to live and survive. There are many
different ways to communicate for centuries, yet there are mainly three ways for today's world: spoken,
written and sign languages. According to research on the language usage of deaf people, they commonly
prefer sign language over other ways. Most of the times they need helpers and/or interpreters on daily life
and they are accompanied by human helpers. We intend to make a bidirectional dynamic machine
translation system by using an example-based approach, and apply between Turkish and Turkish Sign
Language (TSL) glosses for the first time in literature with the belief of one day this novel work on Turkish
would help these people to live independently. Using BLEU and TER metrics for evaluation, we tested our
system considering many conditions, and got competitive results especially compared to previous work in
this field.
Robust Text Watermarking Technique for Authorship Protection of Hindi Languag...CSCJournals
Digital text documents have become a significantly important part on the Internet. A large number of users are attracted towards this digital form of text documents. But some security threats also arise concurrently. The digital libraries offer effective ways to access educational materials, government e-documents, financial documents, social media contents and many others. However content authorship and tamper detection of all these digital text documents require special attention. Till now, considerably very few digital watermarking techniques exist for text documents. In this paper, we propose a method for effective watermarking of Hindi language text documents. Hindi stands second among all languages across the world. It has widespread availability of its digital contents of various types. In proposed technique, the watermark is logically embedded in the text using 'swar' (vowel) as a special feature of the Hindi language, supported by suitable encryption. In extraction phase the Certificate Authority (CA) plays an important role in the authorship protection process as a trusted third party. The text is decrypted and watermark is extracted to prove genuine authorship. Our technique has been tested for various types of feasible text attacks with different embedding frequency.
SENTIMENT ANALYSIS OF MIXED CODE FOR THE TRANSLITERATED HINDI AND MARATHI TEXTSijnlc
The evolution of information Technology has led to the collection of large amount of data, the volume of
which has increased to the extent that in last two years the data produced is greater than all the data ever
recorded in human history. This has necessitated use of machines to understand, interpret and apply data,
without manual involvement. A lot of these texts are available in transliterated code-mixed form, which due
to the complexity are very difficult to analyze. The work already performed in this area is progressing at
great pace and this work hopes to be a way to push that work further. The designed system is an effort
which classifies Hindi as well as Marathi text transliterated (Romanized) documents automatically using
supervised learning methods (KNN), Naïve Bayes and Support Vector Machine (SVM)) and ontology based
classification; and results are compared to in order to decide which methodology is better suited in
handling of these documents. As we will see, the plain machine learning algorithm applications are just as
or in many cases are much better in performance than the more analytical approach.
Legal translator as a communicator. A review of Borja Albi and Prieto RamosLucja Biel
A review of Borja Albi, Anabel and Fernando Prieto Ramos (eds): Legal Translation in Context. Professional Issues and Prospects: Series New Trends in Translation Studies, 2013, Peter Lang, Oxford, Vol. 4, 315 pp
Automatic classification of bengali sentences based on sense definitions pres...ijctcm
Based on the sense definition of words available in the Bengali WordNet, an attempt is made to classify the
Bengali sentences automatically into different groups in accordance with their underlying senses. The input
sentences are collected from 50 different categories of the Bengali text corpus developed in the TDIL
project of the Govt. of India, while information about the different senses of particular ambiguous lexical
item is collected from Bengali WordNet. In an experimental basis we have used Naive Bayes probabilistic
model as a useful classifier of sentences. We have applied the algorithm over 1747 sentences that contain a
particular Bengali lexical item which, because of its ambiguous nature, is able to trigger different senses
that render sentences in different meanings. In our experiment we have achieved around 84% accurate
result on the sense classification over the total input sentences. We have analyzed those residual sentences
that did not comply with our experiment and did affect the results to note that in many cases, wrong
syntactic structures and less semantic information are the main hurdles in semantic classification of
sentences. The applicational relevance of this study is attested in automatic text classification, machine
learning, information extraction, and word sense disambiguation
A New Approach: Automatically Identify Proper Noun from Bengali Sentence for ...Syeful Islam
More than hundreds of millions of people of almost all levels of education and attitudes from different country communicate with
each other for different using various languages. Machine translation is highly demanding due to increasing the usage of web
based Communication. One of the major problem of Bengali translation is identified a naming word from a sentence, which is
relatively simple in English language, because such entities start with a capital letter. In Bangla we do not have concept of small
or capital letters and there is huge no. of different naming entity available in Bangla. Thus we find difficulties in understanding
whether a word is a proper noun or not. Here we have introduce a new approach to identify proper noun from a Bengali sentence
for UNL without storing huge no. of naming entity in word dictionary. The goal is to make possible Bangla sentence conversion
to UNL and vice versa with minimal storing word in dictionary.
Keyword Extraction Based Summarization of Categorized Kannada Text Documents ijsc
The internet has caused a humongous growth in the number of documents available online. Summaries of documents can help find the right information and are particularly effective when the document base is very large. Keywords are closely associated to a document as they reflect the document's content and act as indices for a given document. In this work, we present a method to produce extractive summaries of documents in the Kannada language, given number of sentences as limitation. The algorithm extracts key words from pre-categorized Kannada documents collected from online resources. We use two feature selection techniques for obtaining features from documents, then we combine scores obtained by GSS (Galavotti, Sebastiani, Simi) coefficients and IDF (Inverse Document Frequency) methods along with TF (Term Frequency) for extracting key words and later use these for summarization based on rank of the sentence. In the current implementation, a document from a given category is selected from our database and depending on the number of sentences given by the user, a summary is generated.
Introduction - Lost in the Eurofog: The Textual Fit of Translated LawLucja Biel
The book is one of the few in-depth investigations into the nature of EU legal translation and its impact on national legal languages. It is also the first attempt to characterise EU Polish, a language of supranational law and a hybrid variant of legal Polish emerging via translation. The book applies Chesterman’s concept of textual fit, that is how translations differ from non-translations, to demonstrate empirically on large corpora how the Polish eurolect departs from the conventions of legal and general Polish both at the macrostructural and the microstructural level. The findings are juxtaposed with the pre-accession version of Polish law to track the «Europeanisation» of legal Polish – recent changes brought about by the unprecedented inflow of EU translations.
Natural Language Processing Theory, Applications and Difficultiesijtsrd
The promise of a powerful computing device to help people in productivity as well as in recreation can only be realized with proper human machine communication. Automatic recognition and understanding of spoken language is the first step toward natural human machine interaction. Research in this field has produced remarkable results, leading to many exciting expectations and new challenges. This field is known as Natural language Processing. In this paper the natural language generation and Natural language understanding is discussed. Difficulties in NLU, applications and comparison with structured programming language are also discussed here. Mrs. Anjali Gharat | Mrs. Helina Tandel | Mr. Ketan Bagade "Natural Language Processing Theory, Applications and Difficulties" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-6 , October 2019, URL: https://www.ijtsrd.com/papers/ijtsrd28092.pdf Paper URL: https://www.ijtsrd.com/engineering/computer-engineering/28092/natural-language-processing-theory-applications-and-difficulties/mrs-anjali-gharat
https://www.learntek.org/blog/natural-language-processing-applications/
Learntek is global online training provider on Big Data Analytics, Hadoop, Machine Learning, Deep Learning, IOT, AI, Cloud Technology, DEVOPS, Digital Marketing and other IT and Management courses.
‘A PERSISTENT SOURCE OF DISQUIET’28: AN INVESTIGATION OF THE CULTURAL CAPITAL...ijejournal
This paper discusses the findings of a cultural content analysis conducted on the reading component of
twenty IELTS exams. A total of sixty reading passages were examined for cultural capital. The study found
that, on average, one reading test contained fourteen cultural references in terms of a variety of cultural
elements including cultural objects and historical settings. Geographically speaking, the readings referred
to 139 places or regions around the world with only five references pertaining to the Middle East and none
to the United Arab Emirates where this study was conducted.
ISSUES AND CHALLENGES IN MARATHI NAMED ENTITY RECOGNITIONijnlc
Information Extraction (IE) is a sub discipline of Artificial Intelligence. IE identifies information in
unstructured information source that adheres to predefined semantics i.e. people, location etc. Recognition
of named entities (NEs) from computer readable natural language text is significant task of IE and natural
language processing (NLP). Named entity (NE) extraction is important step for processing unstructured
content. Unstructured data is computationally opaque. Computers require computationally transparent
data for processing. IE adds meaning to raw data so that it can be easily processed by computers. There
are various different approaches that are applied for extraction of entities from text. This paper elaborates
need of NE recognition for Marathi and discusses issues and challenges involved in NE recognition tasks
for Marathi language. It also explores various methods and techniques that are useful for creation of
learning resources and lexicons that are important for extraction of NEs from natural language
unstructured text.
Automated Discovery of Logical Fallacies in Legal Argumentationgerogepatton
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur
fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog.
Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff,
the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for
detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every
premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at
each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well
as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of
validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
AUTOMATED DISCOVERY OF LOGICAL FALLACIES IN LEGAL ARGUMENTATIONijaia
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog. Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff, the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
AUTOMATED DISCOVERY OF LOGICAL FALLACIES IN LEGAL ARGUMENTATIONgerogepatton
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog. Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff, the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
BIDIRECTIONAL MACHINE TRANSLATION BETWEEN TURKISH AND TURKISH SIGN LANGUAGE: ...ijnlc
Communication is one of the first necessities for human beings to live and survive. There are many
different ways to communicate for centuries, yet there are mainly three ways for today's world: spoken,
written and sign languages. According to research on the language usage of deaf people, they commonly
prefer sign language over other ways. Most of the times they need helpers and/or interpreters on daily life
and they are accompanied by human helpers. We intend to make a bidirectional dynamic machine
translation system by using an example-based approach, and apply between Turkish and Turkish Sign
Language (TSL) glosses for the first time in literature with the belief of one day this novel work on Turkish
would help these people to live independently. Using BLEU and TER metrics for evaluation, we tested our
system considering many conditions, and got competitive results especially compared to previous work in
this field.
Robust Text Watermarking Technique for Authorship Protection of Hindi Languag...CSCJournals
Digital text documents have become a significantly important part on the Internet. A large number of users are attracted towards this digital form of text documents. But some security threats also arise concurrently. The digital libraries offer effective ways to access educational materials, government e-documents, financial documents, social media contents and many others. However content authorship and tamper detection of all these digital text documents require special attention. Till now, considerably very few digital watermarking techniques exist for text documents. In this paper, we propose a method for effective watermarking of Hindi language text documents. Hindi stands second among all languages across the world. It has widespread availability of its digital contents of various types. In proposed technique, the watermark is logically embedded in the text using 'swar' (vowel) as a special feature of the Hindi language, supported by suitable encryption. In extraction phase the Certificate Authority (CA) plays an important role in the authorship protection process as a trusted third party. The text is decrypted and watermark is extracted to prove genuine authorship. Our technique has been tested for various types of feasible text attacks with different embedding frequency.
SENTIMENT ANALYSIS OF MIXED CODE FOR THE TRANSLITERATED HINDI AND MARATHI TEXTSijnlc
The evolution of information Technology has led to the collection of large amount of data, the volume of
which has increased to the extent that in last two years the data produced is greater than all the data ever
recorded in human history. This has necessitated use of machines to understand, interpret and apply data,
without manual involvement. A lot of these texts are available in transliterated code-mixed form, which due
to the complexity are very difficult to analyze. The work already performed in this area is progressing at
great pace and this work hopes to be a way to push that work further. The designed system is an effort
which classifies Hindi as well as Marathi text transliterated (Romanized) documents automatically using
supervised learning methods (KNN), Naïve Bayes and Support Vector Machine (SVM)) and ontology based
classification; and results are compared to in order to decide which methodology is better suited in
handling of these documents. As we will see, the plain machine learning algorithm applications are just as
or in many cases are much better in performance than the more analytical approach.
Legal translator as a communicator. A review of Borja Albi and Prieto RamosLucja Biel
A review of Borja Albi, Anabel and Fernando Prieto Ramos (eds): Legal Translation in Context. Professional Issues and Prospects: Series New Trends in Translation Studies, 2013, Peter Lang, Oxford, Vol. 4, 315 pp
Automatic classification of bengali sentences based on sense definitions pres...ijctcm
Based on the sense definition of words available in the Bengali WordNet, an attempt is made to classify the
Bengali sentences automatically into different groups in accordance with their underlying senses. The input
sentences are collected from 50 different categories of the Bengali text corpus developed in the TDIL
project of the Govt. of India, while information about the different senses of particular ambiguous lexical
item is collected from Bengali WordNet. In an experimental basis we have used Naive Bayes probabilistic
model as a useful classifier of sentences. We have applied the algorithm over 1747 sentences that contain a
particular Bengali lexical item which, because of its ambiguous nature, is able to trigger different senses
that render sentences in different meanings. In our experiment we have achieved around 84% accurate
result on the sense classification over the total input sentences. We have analyzed those residual sentences
that did not comply with our experiment and did affect the results to note that in many cases, wrong
syntactic structures and less semantic information are the main hurdles in semantic classification of
sentences. The applicational relevance of this study is attested in automatic text classification, machine
learning, information extraction, and word sense disambiguation
A New Approach: Automatically Identify Proper Noun from Bengali Sentence for ...Syeful Islam
More than hundreds of millions of people of almost all levels of education and attitudes from different country communicate with
each other for different using various languages. Machine translation is highly demanding due to increasing the usage of web
based Communication. One of the major problem of Bengali translation is identified a naming word from a sentence, which is
relatively simple in English language, because such entities start with a capital letter. In Bangla we do not have concept of small
or capital letters and there is huge no. of different naming entity available in Bangla. Thus we find difficulties in understanding
whether a word is a proper noun or not. Here we have introduce a new approach to identify proper noun from a Bengali sentence
for UNL without storing huge no. of naming entity in word dictionary. The goal is to make possible Bangla sentence conversion
to UNL and vice versa with minimal storing word in dictionary.
Keyword Extraction Based Summarization of Categorized Kannada Text Documents ijsc
The internet has caused a humongous growth in the number of documents available online. Summaries of documents can help find the right information and are particularly effective when the document base is very large. Keywords are closely associated to a document as they reflect the document's content and act as indices for a given document. In this work, we present a method to produce extractive summaries of documents in the Kannada language, given number of sentences as limitation. The algorithm extracts key words from pre-categorized Kannada documents collected from online resources. We use two feature selection techniques for obtaining features from documents, then we combine scores obtained by GSS (Galavotti, Sebastiani, Simi) coefficients and IDF (Inverse Document Frequency) methods along with TF (Term Frequency) for extracting key words and later use these for summarization based on rank of the sentence. In the current implementation, a document from a given category is selected from our database and depending on the number of sentences given by the user, a summary is generated.
Introduction - Lost in the Eurofog: The Textual Fit of Translated LawLucja Biel
The book is one of the few in-depth investigations into the nature of EU legal translation and its impact on national legal languages. It is also the first attempt to characterise EU Polish, a language of supranational law and a hybrid variant of legal Polish emerging via translation. The book applies Chesterman’s concept of textual fit, that is how translations differ from non-translations, to demonstrate empirically on large corpora how the Polish eurolect departs from the conventions of legal and general Polish both at the macrostructural and the microstructural level. The findings are juxtaposed with the pre-accession version of Polish law to track the «Europeanisation» of legal Polish – recent changes brought about by the unprecedented inflow of EU translations.
Natural Language Processing Theory, Applications and Difficultiesijtsrd
The promise of a powerful computing device to help people in productivity as well as in recreation can only be realized with proper human machine communication. Automatic recognition and understanding of spoken language is the first step toward natural human machine interaction. Research in this field has produced remarkable results, leading to many exciting expectations and new challenges. This field is known as Natural language Processing. In this paper the natural language generation and Natural language understanding is discussed. Difficulties in NLU, applications and comparison with structured programming language are also discussed here. Mrs. Anjali Gharat | Mrs. Helina Tandel | Mr. Ketan Bagade "Natural Language Processing Theory, Applications and Difficulties" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-6 , October 2019, URL: https://www.ijtsrd.com/papers/ijtsrd28092.pdf Paper URL: https://www.ijtsrd.com/engineering/computer-engineering/28092/natural-language-processing-theory-applications-and-difficulties/mrs-anjali-gharat
https://www.learntek.org/blog/natural-language-processing-applications/
Learntek is global online training provider on Big Data Analytics, Hadoop, Machine Learning, Deep Learning, IOT, AI, Cloud Technology, DEVOPS, Digital Marketing and other IT and Management courses.
‘A PERSISTENT SOURCE OF DISQUIET’28: AN INVESTIGATION OF THE CULTURAL CAPITAL...ijejournal
This paper discusses the findings of a cultural content analysis conducted on the reading component of
twenty IELTS exams. A total of sixty reading passages were examined for cultural capital. The study found
that, on average, one reading test contained fourteen cultural references in terms of a variety of cultural
elements including cultural objects and historical settings. Geographically speaking, the readings referred
to 139 places or regions around the world with only five references pertaining to the Middle East and none
to the United Arab Emirates where this study was conducted.
ISSUES AND CHALLENGES IN MARATHI NAMED ENTITY RECOGNITIONijnlc
Information Extraction (IE) is a sub discipline of Artificial Intelligence. IE identifies information in
unstructured information source that adheres to predefined semantics i.e. people, location etc. Recognition
of named entities (NEs) from computer readable natural language text is significant task of IE and natural
language processing (NLP). Named entity (NE) extraction is important step for processing unstructured
content. Unstructured data is computationally opaque. Computers require computationally transparent
data for processing. IE adds meaning to raw data so that it can be easily processed by computers. There
are various different approaches that are applied for extraction of entities from text. This paper elaborates
need of NE recognition for Marathi and discusses issues and challenges involved in NE recognition tasks
for Marathi language. It also explores various methods and techniques that are useful for creation of
learning resources and lexicons that are important for extraction of NEs from natural language
unstructured text.
Automated Discovery of Logical Fallacies in Legal Argumentationgerogepatton
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur
fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog.
Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff,
the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for
detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every
premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at
each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well
as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of
validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
AUTOMATED DISCOVERY OF LOGICAL FALLACIES IN LEGAL ARGUMENTATIONijaia
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog. Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff, the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
AUTOMATED DISCOVERY OF LOGICAL FALLACIES IN LEGAL ARGUMENTATIONgerogepatton
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog. Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff, the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
AUTOMATED DISCOVERY OF LOGICAL FALLACIES IN LEGAL ARGUMENTATIONgerogepatton
This paper presents a model of an algorithmic framework and a system for the discovery of non sequitur fallacies in legal argumentation. The model functions on formalised legal text implemented in Prolog. Different parts of the formalised legal text for legal decision-making processes such as, claim of a plaintiff, the piece of law applied to the case, and the decision of judge, will be assessed by the algorithm, for detecting fallacies in an argument. We provide a mechanism designed to assess the coherence of every premise of a claim, their logic structure and legal consistency, with their corresponding piece of law at each stage of the argumentation. The modelled system checks for validity and soundness of a claim, as well as sufficiency and necessity of the premise of arguments. We assert that, dealing with the challenges of validity, soundness, sufficiency and necessity resolves fallacies in argumentation.
AN INTERSEMIOTIC TRANSLATION OF NORMATIVE UTTERANCES TO MACHINE LANGUAGEIJwest
Programming Languages (PL) effectively performs an intersemiotic translation from a natural language to
machine language. PL comprises a set of instructions to implement algorithms, i.e., to perform
(computational) tasks. Similarly to Normative Languages (NoL), PLs are formal languages that can
perform both regulative and constitutive functions. The paper presents the first results of interdisciplinary
research aimed at highlighting the similarities between NoL (social sciences) and PL (computer science)
through everyday life examples, exploiting Object-Oriented Programming Language tools and an Internet
of Things (IoT) system as a case study. Given the pandemic emergency, the urge to move part of our social
life to the digital world arose, together with the need to effectively transpose regulative rules and
constitutive rules through different strategies for translating a normative utterance expressed in natural
language.
A NATURAL LOGIC FOR ARTIFICIAL INTELLIGENCE, AND ITS RISKS AND BENEFITSijwscjournal
This paper is a multidisciplinary project proposal, submitted in the hopes that it may garner
enough interest to launch it with members of the AI research community along with linguists
and philosophers of mind and language interested in constructing a semantics for a natural
logic for AI. The paper outlines some of the major hurdles in the way of “semantics-driven”
natural language processing based on standard predicate logic and sketches out the steps to be
taken toward a “natural logic”, a semantic system explicitly defined on a well-regimented (but
indefinitely expandable) fragment of a natural language that can, therefore, be “intelligently”
processed by computers, using the semantic representations of the phrases of the fragment.
A Natural Logic for Artificial Intelligence, and its Risks and Benefits gerogepatton
This paper is a multidisciplinary project proposal, submitted in the hopes that it may garner enough interest to launch it with members of the AI research community along with linguists
and philosophers of mind and language interested in constructing a semantics for a natural logic for AI. The paper outlines some of the major hurdles in the way of “semantics-driven” natural language processing based on standard predicate logic and sketches out the steps to be
taken toward a “natural logic”, a semantic system explicitly defined on a well-regimented (but indefinitely expandable) fragment of a natural language that can, therefore, be “intelligently” processed by computers, using the semantic representations of the phrases of the fragment.
A NATURAL LOGIC FOR ARTIFICIAL INTELLIGENCE, AND ITS RISKS AND BENEFITSijasuc
This paper is a multidisciplinary project proposal, submitted in the hopes that it may garner
enough interest to launch it with members of the AI research community along with linguists
and philosophers of mind and language interested in constructing a semantics for a natural
logic for AI. The paper outlines some of the major hurdles in the way of “semantics-driven”
natural language processing based on standard predicate logic and sketches out the steps to be
taken toward a “natural logic”, a semantic system explicitly defined on a well-regimented (but
indefinitely expandable) fragment of a natural language that can, therefore, be “intelligently”
processed by computers, using the semantic representations of the phrases of the fragment.
Review of Parsing in Modern Greek - A New ApproachCSCJournals
This paper deals with the attempts of parsing Modern Greek language and the techniques used. Most attempts are described without being thoroughly analyzed for the purpose of reviewing and comparing methods. The desire to use Link and Relational Grammars for the syntactic analysis of Greek language is also stated. Link Grammar has a robust algorithmic structure, while Relational Grammar present results in a standard and commonly understandable manner. Therefore, their combination is expected to facilitate the presentation of results in a more user-friendly manner, and to exhibit a better processing efficiency.
In recent years, great advances have been made in the speed, accuracy, and coverage of automatic word
sense disambiguator systems that, given a word appearing in a certain context, can identify the sense of
that word. In this paper we consider the problem of deciding whether same words contained in different
documents are related to the same meaning or are homonyms. Our goal is to improve the estimate of the
similarity of documents in which some words may be used with different meanings. We present three new
strategies for solving this problem, which are used to filter out homonyms from the similarity computation.
Two of them are intrinsically non-semantic, whereas the other one has a semantic flavor and can also be
applied to word sense disambiguation. The three strategies have been embedded in an article document
recommendation system that one of the most important Italian ad-serving companies offers to its customers.
Domain Specific Terminology Extraction (ICICT 2006)IT Industry
Imran Sarwar Bajwa, M. Imran Siddique, M. Abbas Choudhary, [2006], "Automatic Domain Specific Terminology Extraction using a Decision Support System", in IEEE 4th International Conference on Information and Communication Technology (ICICT 2006), Cairo, Egypt. pp:651-659
In recent years, great advances have been made in the speed, accuracy, and coverage of automatic word
sense disambiguator systems that, given a word appearing in a certain context, can identify the sense of
that word. In this paper we consider the problem of deciding whether same words contained in different
documents are related to the same meaning or are homonyms. Our goal is to improve the estimate of the
similarity of documents in which some words may be used with different meanings. We present three new
strategies for solving this problem, which are used to filter out homonyms from the similarity computation.
Two of them are intrinsically non-semantic, whereas the other one has a semantic flavor and can also be
applied to word sense disambiguation. The three strategies have been embedded in an article document
recommendation system that one of the most important Italian ad-serving companies offers to its customers
The fundamental difference between cognitive grammar and generative grammar is that
cognitive ability is offered in generative grammar. However, according to cognitive grammar, no
individual cognitive ability is necessary for describing language abilities. Cognitive ability,
recognised by psychology and other branches of knowledge, is used to create human language
ability. In any grammar, language skills are analysed by describing the nature of grammatical
knowledge. The grammatical knowledge of humans is the combination of symbolic units. Those
units are members of several categories, and different symbolic units can construct the mechanism.
From linguistic attention, it can fully be described the way, from a particular scene, how the
constructions create a speech. This article discusses the theory of cognitive grammar from a
fundamental point of view.
Similar to CITIZENSHIP ACT (591) OF GHANA AS A LOGIC THEOREM AND ITS SEMANTIC IMPLICATIONS (20)
Effect of Query Formation on Web Search Engine Resultskevig
Query in a search engine is generally based on natural language. A query can be expressed in more than
one way without changing its meaning as it depends on thinking of human being at a particular moment.
Aim of the searcher is to get most relevant results immaterial of how the query has been expressed. In the
present paper, we have examined the results of search engine for change in coverage and similarity of first
few results when a query is entered in two semantically same but in different formats. Searching has been
made through Google search engine. Fifteen pairs of queries have been chosen for the study. The t-test has
been used for the purpose and the results have been checked on the basis of total documents found,
similarity of first five and first ten documents found in the results of a query entered in two different
formats. It has been found that the total coverage is same but first few results are significantly different.
Investigations of the Distributions of Phonemic Durations in Hindi and Dogrikevig
Speech generation is one of the most important areas of research in speech signal processing which is now gaining a serious attention. Speech is a natural form of communication in all living things. Computers with the ability to understand speech and speak with a human like voice are expected to contribute to the development of more natural man-machine interface. However, in order to give those functions that are even closer to those of human beings, we must learn more about the mechanisms by which speech is produced and perceived, and develop speech information processing technologies that can generate a more natural sounding systems. The so described field of stud, also called speech synthesis and more prominently acknowledged as text-to-speech synthesis, originated in the mid eighties because of the emergence of DSP and the rapid advancement of VLSI techniques. To understand this field of speech, it is necessary to understand the basic theory of speech production. Every language has different phonetic alphabets and a different set of possible phonemes and their combinations.
For the analysis of the speech signal, we have carried out the recording of five speakers in Dogri (3 male and 5 females) and eight speakers in Hindi language (4 male and 4 female). For estimating the durational distributions, the mean of mean of ten instances of vowels of each speaker in both the languages has been calculated. Investigations have shown that the two durational distributions differ significantly with respect to mean and standard deviation. The duration of phoneme is speaker dependent. The whole investigation can be concluded with the end result that almost all the Dogri phonemes have shorter duration, in comparison to Hindi phonemes. The period in milli seconds of same phonemes when uttered in Hindi were found to be longer compared to when they were spoken by a person with Dogri as his mother tongue. There are many applications which are directly of indirectly related to the research being carried out. For instance the main application may be for transforming Dogri speech into Hindi and vice versa, and further utilizing this application, we can develop a speech aid to teach Dogri to children. The results may also be useful for synthesizing the phonemes of Dogri using the parameters of the phonemes of Hindi and for building large vocabulary speech recognition systems.
May 2024 - Top10 Cited Articles in Natural Language Computingkevig
Natural Language Processing is a programmed approach to analyze text that is based on both a set of theories and a set of technologies. This forum aims to bring together researchers who have designed and build software that will analyze, understand, and generate languages that humans use naturally to address computers.
Effect of Singular Value Decomposition Based Processing on Speech Perceptionkevig
Speech is an important biological signal for primary mode of communication among human being and also the most natural and efficient form of exchanging information among human in speech. Speech processing is the most important aspect in signal processing. In this paper the theory of linear algebra called singular value decomposition (SVD) is applied to the speech signal. SVD is a technique for deriving important parameters of a signal. The parameters derived using SVD may further be reduced by perceptual evaluation of the synthesized speech using only perceptually important parameters, where the speech signal can be compressed so that the information can be transformed into compressed form without losing its quality. This technique finds wide applications in speech compression, speech recognition, and speech synthesis. The objective of this paper is to investigate the effect of SVD based feature selection of the input speech on the perception of the processed speech signal. The speech signal which is in the form of vowels \a\, \e\, \u\ were recorded from each of the six speakers (3 males and 3 females). The vowels for the six speakers were analyzed using SVD based processing and the effect of the reduction in singular values was investigated on the perception of the resynthesized vowels using reduced singular values. Investigations have shown that the number of singular values can be drastically reduced without significantly affecting the perception of the vowels.
Identifying Key Terms in Prompts for Relevance Evaluation with GPT Modelskevig
Relevance evaluation of a query and a passage is essential in Information Retrieval (IR). Recently, numerous studies have been conducted on tasks related to relevance judgment using Large Language Models (LLMs) such as GPT-4,
demonstrating significant improvements. However, the efficacy of LLMs is considerably influenced by the design of the prompt. The purpose of this paper is to
identify which specific terms in prompts positively or negatively impact relevance
evaluation with LLMs. We employed two types of prompts: those used in previous
research and generated automatically by LLMs. By comparing the performance of
these prompts in both few-shot and zero-shot settings, we analyze the influence of
specific terms in the prompts. We have observed two main findings from our study.
First, we discovered that prompts using the term ‘answer’ lead to more effective
relevance evaluations than those using ‘relevant.’ This indicates that a more direct
approach, focusing on answering the query, tends to enhance performance. Second,
we noted the importance of appropriately balancing the scope of ‘relevance.’ While
the term ‘relevant’ can extend the scope too broadly, resulting in less precise evaluations, an optimal balance in defining relevance is crucial for accurate assessments.
The inclusion of few-shot examples helps in more precisely defining this balance.
By providing clearer contexts for the term ‘relevance,’ few-shot examples contribute
to refine relevance criteria. In conclusion, our study highlights the significance of
carefully selecting terms in prompts for relevance evaluation with LLMs.
Identifying Key Terms in Prompts for Relevance Evaluation with GPT Modelskevig
Relevance evaluation of a query and a passage is essential in Information Retrieval (IR). Recently, numerous studies have been conducted on tasks related to relevance judgment using Large Language Models (LLMs) such as GPT-4, demonstrating significant improvements. However, the efficacy of LLMs is considerably influenced by the design of the prompt. The purpose of this paper is to identify which specific terms in prompts positively or negatively impact relevance evaluation with LLMs. We employed two types of prompts: those used in previous research and generated automatically by LLMs. By comparing the performance of these prompts in both few-shot and zero-shot settings, we analyze the influence of specific terms in the prompts. We have observed two main findings from our study. First, we discovered that prompts using the term ‘answer’ lead to more effective relevance evaluations than those using ‘relevant.’ This indicates that a more direct approach, focusing on answering the query, tends to enhance performance. Second, we noted the importance of appropriately balancing the scope of ‘relevance.’ While the term ‘relevant’ can extend the scope too broadly, resulting in less precise evaluations, an optimal balance in defining relevance is crucial for accurate assessments. The inclusion of few-shot examples helps in more precisely defining this balance. By providing clearer contexts for the term ‘relevance,’ few-shot examples contribute to refine relevance criteria. In conclusion, our study highlights the significance of carefully selecting terms in prompts for relevance evaluation with LLMs.
Genetic Approach For Arabic Part Of Speech Taggingkevig
With the growing number of textual resources available, the ability to understand them becomes critical.
An essential first step in understanding these sources is the ability to identify the parts-of-speech in each
sentence. Arabic is a morphologically rich language, which presents a challenge for part of speech
tagging. In this paper, our goal is to propose, improve, and implement a part-of-speech tagger based on a
genetic algorithm. The accuracy obtained with this method is comparable to that of other probabilistic
approaches.
Rule Based Transliteration Scheme for English to Punjabikevig
Machine Transliteration has come out to be an emerging and a very important research area in the field of
machine translation. Transliteration basically aims to preserve the phonological structure of words. Proper
transliteration of name entities plays a very significant role in improving the quality of machine translation.
In this paper we are doing machine transliteration for English-Punjabi language pair using rule based
approach. We have constructed some rules for syllabification. Syllabification is the process to extract or
separate the syllable from the words. In this we are calculating the probabilities for name entities (Proper
names and location). For those words which do not come under the category of name entities, separate
probabilities are being calculated by using relative frequency through a statistical machine translation
toolkit known as MOSES. Using these probabilities we are transliterating our input text from English to
Punjabi.
Improving Dialogue Management Through Data Optimizationkevig
In task-oriented dialogue systems, the ability for users to effortlessly communicate with machines and computers through natural language stands as a critical advancement. Central to these systems is the dialogue manager, a pivotal component tasked with navigating the conversation to effectively meet user goals by selecting the most appropriate response. Traditionally, the development of sophisticated dialogue management has embraced a variety of methodologies, including rule-based systems, reinforcement learning, and supervised learning, all aimed at optimizing response selection in light of user inputs. This research casts a spotlight on the pivotal role of data quality in enhancing the performance of dialogue managers. Through a detailed examination of prevalent errors within acclaimed datasets, such as Multiwoz 2.1 and SGD, we introduce an innovative synthetic dialogue generator designed to control the introduction of errors precisely. Our comprehensive analysis underscores the critical impact of dataset imperfections, especially mislabeling, on the challenges inherent in refining dialogue management processes.
Document Author Classification using Parsed Language Structurekevig
Over the years there has been ongoing interest in detecting authorship of a text based on statistical properties of the text, such as by using occurrence rates of noncontextual words. In previous work, these techniques have been used, for example, to determine authorship of all of The Federalist Papers. Such methods may be useful in more modern times to detect fake or AI authorship. Progress in statistical natural language parsers introduces the possibility of using grammatical structure to detect authorship. In this paper we explore a new possibility for detecting authorship using grammatical structural information extracted using a statistical natural language parser. This paper provides a proof of concept, testing author classification based on grammatical structure on a set of “proof texts,” The Federalist Papers and Sanditon which have been as test cases in previous authorship detection studies. Several features extracted from the statisticalnaturallanguage parserwere explored: all subtrees of some depth from any level; rooted subtrees of some depth, part of speech, and part of speech by level in the parse tree. It was found to be helpful to project the features into a lower dimensional space. Statistical experiments on these documents demonstrate that information from a statistical parser can, in fact, assist in distinguishing authors.
Rag-Fusion: A New Take on Retrieval Augmented Generationkevig
Infineon has identified a need for engineers, account managers, and customers to rapidly obtain product information. This problem is traditionally addressed with retrieval-augmented generation (RAG) chatbots, but in this study, I evaluated the use of the newly popularized RAG-Fusion method. RAG-Fusion combines RAG and reciprocal rank fusion (RRF) by generating multiple queries, reranking them with reciprocal scores and fusing the documents and scores. Through manually evaluating answers on accuracy, relevance, and comprehensiveness, I found that RAG-Fusion was able to provide accurate and comprehensive answers due to the generated queries contextualizing the original query from various perspectives. However, some answers strayed off topic when the generated queries' relevance to the original query is insufficient. This research marks significant progress in artificial intelligence (AI) and natural language processing (NLP) applications and demonstrates transformations in a global and multi-industry context.
Performance, Energy Consumption and Costs: A Comparative Analysis of Automati...kevig
The common practice in Machine Learning research is to evaluate the top-performing models based on their performance. However, this often leads to overlooking other crucial aspects that should be given careful consideration. In some cases, the performance differences between various approaches may be insignificant, whereas factors like production costs, energy consumption, and carbon footprint should be taken into account. Large Language Models (LLMs) are widely used in academia and industry to address NLP problems. In this study, we present a comprehensive quantitative comparison between traditional approaches (SVM-based) and more recent approaches such as LLM (BERT family models) and generative models (GPT2 and LLAMA2), using the LexGLUE benchmark. Our evaluation takes into account not only performance parameters (standard indices), but also alternative measures such as timing, energy consumption and costs, which collectively contribute to the carbon footprint. To ensure a complete analysis, we separately considered the prototyping phase (which involves model selection through training-validation-test iterations) and the in-production phases. These phases follow distinct implementation procedures and require different resources. The results indicate that simpler algorithms often achieve performance levels similar to those of complex models (LLM and generative models), consuming much less energy and requiring fewer resources. These findings suggest that companies should consider additional considerations when choosing machine learning (ML) solutions. The analysis also demonstrates that it is increasingly necessary for the scientific world to also begin to consider aspects of energy consumption in model evaluations, in order to be able to give real meaning to the results obtained using standard metrics (Precision, Recall, F1 and so on).
Evaluation of Medium-Sized Language Models in German and English Languagekevig
Large language models (LLMs) have garnered significant attention, but the definition of “large” lacks clarity. This paper focuses on medium-sized language models (MLMs), defined as having at least six billion parameters but less than 100 billion. The study evaluates MLMs regarding zero-shot generative question answering, which requires models to provide elaborate answers without external document retrieval. The paper introduces an own test dataset and presents results from human evaluation. Results show that combining the best answers from different MLMs yielded an overall correct answer rate of 82.7% which is better than the 60.9% of ChatGPT. The best MLM achieved 71.8% and has 33B parameters, which highlights the importance of using appropriate training data for fine-tuning rather than solely relying on the number of parameters. More fine-grained feedback should be used to further improve the quality of answers. The open source community is quickly closing the gap to the best commercial models.
IMPROVING DIALOGUE MANAGEMENT THROUGH DATA OPTIMIZATIONkevig
In task-oriented dialogue systems, the ability for users to effortlessly communicate with machines and
computers through natural language stands as a critical advancement. Central to these systems is the
dialogue manager, a pivotal component tasked with navigating the conversation to effectively meet user
goals by selecting the most appropriate response. Traditionally, the development of sophisticated dialogue
management has embraced a variety of methodologies, including rule-based systems, reinforcement
learning, and supervised learning, all aimed at optimizing response selection in light of user inputs. This
research casts a spotlight on the pivotal role of data quality in enhancing the performance of dialogue
managers. Through a detailed examination of prevalent errors within acclaimed datasets, such as
Multiwoz 2.1 and SGD, we introduce an innovative synthetic dialogue generator designed to control the
introduction of errors precisely. Our comprehensive analysis underscores the critical impact of dataset
imperfections, especially mislabeling, on the challenges inherent in refining dialogue management
processes.
Document Author Classification Using Parsed Language Structurekevig
Over the years there has been ongoing interest in detecting authorship of a text based on statistical properties of the
text, such as by using occurrence rates of noncontextual words. In previous work, these techniques have been used,
for example, to determine authorship of all of The Federalist Papers. Such methods may be useful in more modern
times to detect fake or AI authorship. Progress in statistical natural language parsers introduces the possibility of
using grammatical structure to detect authorship. In this paper we explore a new possibility for detecting authorship
using grammatical structural information extracted using a statistical natural language parser. This paper provides a
proof of concept, testing author classification based on grammatical structure on a set of “proof texts,” The Federalist
Papers and Sanditon which have been as test cases in previous authorship detection studies. Several features extracted
of some depth, part of speech, and part of speech by level in the parse tree. It was found to be helpful to project the
features into a lower dimensional space. Statistical experiments on these documents demonstrate that information
from a statistical parser can, in fact, assist in distinguishing authors.
RAG-FUSION: A NEW TAKE ON RETRIEVALAUGMENTED GENERATIONkevig
Infineon has identified a need for engineers, account managers, and customers to rapidly obtain product
information. This problem is traditionally addressed with retrieval-augmented generation (RAG) chatbots,
but in this study, I evaluated the use of the newly popularized RAG-Fusion method. RAG-Fusion combines
RAG and reciprocal rank fusion (RRF) by generating multiple queries, reranking them with reciprocal
scores and fusing the documents and scores. Through manually evaluating answers on accuracy,
relevance, and comprehensiveness, I found that RAG-Fusion was able to provide accurate and
comprehensive answers due to the generated queries contextualizing the original query from various
perspectives. However, some answers strayed off topic when the generated queries' relevance to the
original query is insufficient. This research marks significant progress in artificial intelligence (AI) and
natural language processing (NLP) applications and demonstrates transformations in a global and multiindustry context
Performance, energy consumption and costs: a comparative analysis of automati...kevig
The common practice in Machine Learning research is to evaluate the top-performing models based on their
performance. However, this often leads to overlooking other crucial aspects that should be given careful
consideration. In some cases, the performance differences between various approaches may be insignificant, whereas factors like production costs, energy consumption, and carbon footprint should be taken into
account. Large Language Models (LLMs) are widely used in academia and industry to address NLP problems. In this study, we present a comprehensive quantitative comparison between traditional approaches
(SVM-based) and more recent approaches such as LLM (BERT family models) and generative models (GPT2 and LLAMA2), using the LexGLUE benchmark. Our evaluation takes into account not only performance
parameters (standard indices), but also alternative measures such as timing, energy consumption and costs,
which collectively contribute to the carbon footprint. To ensure a complete analysis, we separately considered the prototyping phase (which involves model selection through training-validation-test iterations) and
the in-production phases. These phases follow distinct implementation procedures and require different resources. The results indicate that simpler algorithms often achieve performance levels similar to those of
complex models (LLM and generative models), consuming much less energy and requiring fewer resources.
These findings suggest that companies should consider additional considerations when choosing machine
learning (ML) solutions. The analysis also demonstrates that it is increasingly necessary for the scientific
world to also begin to consider aspects of energy consumption in model evaluations, in order to be able to
give real meaning to the results obtained using standard metrics (Precision, Recall, F1 and so on).
EVALUATION OF MEDIUM-SIZED LANGUAGE MODELS IN GERMAN AND ENGLISH LANGUAGEkevig
Large language models (LLMs) have garnered significant attention, but the definition of “large” lacks
clarity. This paper focuses on medium-sized language models (MLMs), defined as having at least six
billion parameters but less than 100 billion. The study evaluates MLMs regarding zero-shot generative
question answering, which requires models to provide elaborate answers without external document
retrieval. The paper introduces an own test dataset and presents results from human evaluation. Results
show that combining the best answers from different MLMs yielded an overall correct answer rate of
82.7% which is better than the 60.9% of ChatGPT. The best MLM achieved 71.8% and has 33B
parameters, which highlights the importance of using appropriate training data for fine-tuning rather than
solely relying on the number of parameters. More fine-grained feedback should be used to further improve
the quality of answers. The open source community is quickly closing the gap to the best commercial
models.
Natural Language Processing is a programmed approach to analyze text that is based on both a set of theories and a set of technologies. This forum aims to bring together researchers who have designed and build software that will analyze, understand, and generate languages that humans use naturally to address computers.
Enhanced Retrieval of Web Pages using Improved Page Rank Algorithmkevig
Information Retrieval (IR) is a very important and vast area. While searching for context web returns all
the results related to the query. Identifying the relevant result is most tedious task for a user. Word Sense
Disambiguation (WSD) is the process of identifying the senses of word in textual context, when word has
multiple meanings. We have used the approaches of WSD. This paper presents a Proposed Dynamic Page
Rank algorithm that is improved version of Page Rank Algorithm. The Proposed Dynamic Page Rank
algorithm gives much better results than existing Google’s Page Rank algorithm. To prove this we have
calculated Reciprocal Rank for both the algorithms and presented comparative results.
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
Understanding Inductive Bias in Machine LearningSUTEJAS
This presentation explores the concept of inductive bias in machine learning. It explains how algorithms come with built-in assumptions and preferences that guide the learning process. You'll learn about the different types of inductive bias and how they can impact the performance and generalizability of machine learning models.
The presentation also covers the positive and negative aspects of inductive bias, along with strategies for mitigating potential drawbacks. We'll explore examples of how bias manifests in algorithms like neural networks and decision trees.
By understanding inductive bias, you can gain valuable insights into how machine learning models work and make informed decisions when building and deploying them.
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, we’ll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
We have compiled the most important slides from each speaker's presentation. This year’s compilation, available for free, captures the key insights and contributions shared during the DfMAy 2024 conference.
Low power architecture of logic gates using adiabatic techniquesnooriasukmaningtyas
The growing significance of portable systems to limit power consumption in ultra-large-scale-integration chips of very high density, has recently led to rapid and inventive progresses in low-power design. The most effective technique is adiabatic logic circuit design in energy-efficient hardware. This paper presents two adiabatic approaches for the design of low power circuits, modified positive feedback adiabatic logic (modified PFAL) and the other is direct current diode based positive feedback adiabatic logic (DC-DB PFAL). Logic gates are the preliminary components in any digital circuit design. By improving the performance of basic gates, one can improvise the whole system performance. In this paper proposed circuit design of the low power architecture of OR/NOR, AND/NAND, and XOR/XNOR gates are presented using the said approaches and their results are analyzed for powerdissipation, delay, power-delay-product and rise time and compared with the other adiabatic techniques along with the conventional complementary metal oxide semiconductor (CMOS) designs reported in the literature. It has been found that the designs with DC-DB PFAL technique outperform with the percentage improvement of 65% for NOR gate and 7% for NAND gate and 34% for XNOR gate over the modified PFAL techniques at 10 MHz respectively.
6th International Conference on Machine Learning & Applications (CMLA 2024)ClaraZara1
6th International Conference on Machine Learning & Applications (CMLA 2024) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications.
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTjpsjournal1
The rivalry between prominent international actors for dominance over Central Asia's hydrocarbon
reserves and the ancient silk trade route, along with China's diplomatic endeavours in the area, has been
referred to as the "New Great Game." This research centres on the power struggle, considering
geopolitical, geostrategic, and geoeconomic variables. Topics including trade, political hegemony, oil
politics, and conventional and nontraditional security are all explored and explained by the researcher.
Using Mackinder's Heartland, Spykman Rimland, and Hegemonic Stability theories, examines China's role
in Central Asia. This study adheres to the empirical epistemological method and has taken care of
objectivity. This study analyze primary and secondary research documents critically to elaborate role of
china’s geo economic outreach in central Asian countries and its future prospect. China is thriving in trade,
pipeline politics, and winning states, according to this study, thanks to important instruments like the
Shanghai Cooperation Organisation and the Belt and Road Economic Initiative. According to this study,
China is seeing significant success in commerce, pipeline politics, and gaining influence on other
governments. This success may be attributed to the effective utilisation of key tools such as the Shanghai
Cooperation Organisation and the Belt and Road Economic Initiative.
HEAP SORT ILLUSTRATED WITH HEAPIFY, BUILD HEAP FOR DYNAMIC ARRAYS.
Heap sort is a comparison-based sorting technique based on Binary Heap data structure. It is similar to the selection sort where we first find the minimum element and place the minimum element at the beginning. Repeat the same process for the remaining elements.
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
Literature Review Basics and Understanding Reference Management.pptx
CITIZENSHIP ACT (591) OF GHANA AS A LOGIC THEOREM AND ITS SEMANTIC IMPLICATIONS
1. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
DOI: 10.5121/ijnlc.2018.7502 11
CITIZENSHIP ACT (591) OF GHANA AS A LOGIC
THEOREM AND ITS SEMANTIC IMPLICATIONS
NakpihIreneous Callistus
1
Department of Mathematics and Computing, St. John Bosco’s College of Education,
Navrongo, Ghana
ABSTRACT
This paper presents excerpts of the natural text of the Citizenship Act of the Republic of Ghana, ACT 2000
(591), as a logic theorem in First Order Logic (FOL) language. The formalism of this piece of law is done
to allow for semantic analysis of the text by machines. The results of this research also deals with the
problem of ambiguities in the legal text, and reveals the semantic consequence of the natural construction
or textual structure of the piece of law; one major problem of the semantics of legal text has been the
problem of ambiguities, which largely affects interpretations that are alluded to legal statements. Some
constructed sentences sometimes do not reflect the semantic intentions of the composers of the sentences,
due to inherent ambiguities or technical faults in the structure of some parts of the statements. The
formalism of the Act in this paper provides logical proofs and deductions which are asserted to establish
clarity and to reveal semantic errors, or otherwise preserve the semantic intentions of the Act.
KEYWORDS
Natural Language Processing, Formalism, Logic Theorem, Semantic Analysis, Legal text.
1. INTRODUCTION
One of the major challenges in the legal practice is the complexity of expressions of legal
language. Our legal world today is faced with two dimensions of this problem; on one hand they
are faced with the ambiguous use of language and terminologies in legal text that makes it
difficult for comprehension, which sometimes results into the making of fallacious conclusions
which may occur in a claim made, facts established, arguments of lawyers or the decisions of a
judges [1],[2]. On the other hand, they are faced with the complex nature of ambiguities itself
which makes it difficult to identify them when they occur, which for some reason may be genuine
or deliberate [3], or simply elusive [4],[5]. This problem presents different levels of difficulties
for deductive reasoning through legal text for prices decision making.
Legal discourse as done in courts and senate houses have shown that, assessing the logical
implications of legal statements can be a painful exercise and complex to keep track with the
logical connections through all aspects of legal text in application [6]. This is because the natural
expressions of legal text does not make its logical implication apparent just by reading the text;
the use of words, concepts, and judgments is done in almost a codified manner that rather makes
understanding of legal text a challenge through natural or simple processes [7]. This problem has
resulted in some researchers suggesting that, legal text should be composed in what they term as
Plain English [8],[9] whiles others have formulated new writing mechanics for drafting legal text
[10], which they believe would avoid ambiguity and provide comprehensibility to legal text.
Language expressed in any natural form however, will require a system that would explain its
fuzzy aspects and provide understanding to its logical semantics. The problem of semantics of
natural language and information processing has always existed as a natural occurrence in human
2. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
12
communication system. The natural form of expressing human thought and presentation of
information at the best of our reasoning happens with some variances in semantics [11]. One
statement could be expressed to have several meanings, while several statements could also be
expressed to mean the same thing. This in essence reveals the beauty and creativity in natural
language expression, and is not a challenge in human communications by itself, especially in
ordinary communication of life. It is however challenging when other human activities depend on
the right intended meaning of expressed statements, as in the law courts and senate houses.
Much as semantics of natural language can be very tricky, legal expressions presents more
difficult situations, not only in the way it is being expressed, but also in the semantics ascribed to
expressions made [12]. Legal statements as a matter of fact, are difficult to read, and also difficult
to understand, and this is partly because legal statements are constructed with words which are
mostly not familiar in common language expressions. Even practitioners in the domain sometimes
allude different understanding to the same expressed statements in the legal field, and subject the
statements to various argumentation to arrive at decisions [13]. This does not however suggest
that legal statements do not have definite meanings and are therefore open to all kinds of
interpretations. The rules that govern the interpretation of legal statement is quite clear in legal
practice; what remains challenging is the problem of inherent ambiguities, incomprehensibility
and lack of clarity in legal text, due to its form of presentation and fuzziness, and as a result poses
the possibility of implying different meaning to the same legal statements [14], [15].
Natural Language Processing (NLP) is an aspect of Artificial Intelligence (AI) and computational
linguistics that has sought to reconstruct language to close up semantic gaps, using computing
tools[16]. NLP is a broad area that include aspects as different as, automatic translation, or
knowledge acquisition from written or spoken texts. Natural Language Understanding as a branch
of NLP attempts to translate natural language into a precise mathematical formalism in a way that
will capture this informational essence of a text freed from the ambiguity and imprecision of
human languages [17].
Various types of logic, from Description Logic [18] and Horn Logic [19] to First Order Logic
[20], Monadic Second Order[21] and various types of non-monotonic logics [22] have been used
as the target language in this translation process. When it comes to modelling the unconstrained
human languages, all these approaches have had at best partial success in dealing with the
problem of ambiguities in the semantics of language.
Legal language which is structured to preserve, to some extent, a pattern of logic reasoning,
presents an opportunity to use logic as a model of it, with the purpose of reducing as much as
possible, its residual ambiguities. Agreeably, there is a natural relation between logic and law
[23], which has resulted in researchers focusing on the technical development of logic tools
needed to model legal arguments adequately.
In this paper, we choose First Order Logic as a formal language to process a type of legal text, the
Citizenship Act of Ghana, and thus present it as a logic system which reveals the logical
consequences of the natural construction of legal statements, and as well provides a mechanism
for deductive reasoning through the complex relations and logical connections of the all aspects
of the text.
2. LITERATURE SURVEY
The quest to finding absolute means to sound reasoning through expressed natural language in
any form that avoids fallacies, in order to establish lucid semantics of information is not unique to
this research. This research evolved around questions logicians, argumentation theorist,
linguistics, natural language processors, computer scientist and legal practitioners have asked
3. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
13
over centuries up to date. Every domain of discipline has always sought some form of precision
and clarity on how information is understood, presented and shared, with less effort. But the
complexity of human language comes with this natural problem of ambiguity, which leaves
researchers in a position of yet to absolutely bridge the semantic gap.
The idea to automate legal text and the use of computational tools in the law practice dates back
to the 1940s. Some researchers conceived and expressed the idea of an automated information
system for legal practice through Artificial Intelligence research. They indicated that, the
correctness of justice and judgment depends on the mastery of facts and law; the challenge
however remains in the quantity of legislative constructions, statutes, rulings, customs and
practices, economic background and cases that may apply to facts of clients posed to lawyers
engaged in a litigation. They also advanced their ideas to propose an automated legal research
system called Lawdex, which was created based on punch card technology. The proposition of
Lawdex was to be designed as an information retrieval system that leverages efforts to find laws
needed for particular purposes[24].
Some researchers are of the opinion that, applying logic-based techniques and rule-based
reasoning to law, could be a lot more helpful in the development of electronic system in the legal
domain [25]. Logic-based techniques are by far one of the promising ways to deal with
ambiguities in legal text. Anjali and Babu discussed the various types of ambiguities that occur in
natural language and the need for computational tools to resolve them, acknowledging that this is
one of the ways we can have clarity in the presentation of natural language [26]. Agreeably,
research converges to the provision of logical tools for modelling legal language as the niche to
the success of bridging the semantic gap in natural language. These ideas have been tested and a
lot more tools have been built proving some level of success.
Even though computer scientists have proven to use logical tools for processing legal language, it
still remains a debate among legal scholars as to whether logics exactly fits into legal reasoning
and whether the role it plays has primary importance as stipulated by logicians and computer
scientists. Some of these arguments led researchers to present a formal model of legal
argumentation focusing on the reconciliation of symbolic logics and argumentation theories by
reconstructing the fundamental pattern of legal reasoning and further implemented in Prolog
programming language [27]. Sartor’s model advanced the argument that one important necessity
for the analysis and evaluation of legal arguments is formalism, which offers the possibilities of
supporting them with some computing techniques. Real arguments could go through such
evaluation to have its analysed results extended and checked by syntactic computation.
Legal formalism is a description of how legal decisions are supposed to be taken, drawing from
logical structures to undisputable principles applied to facts. Formalism is noted to be a primary
philosophy in decision-making processes in the legal domain, and yet remains to be a
controversial issue among argumentation theorists, lawyers and other researchers.
We agree to some extent, the position of the legal scholars, on the difference between human
reasoning and that of computers; reasoning by intuition and analogy as done by humans, and step
by step algorithmic processes as done by computers are completely distinct. Computers at their
best can perform some case-based reasoning as supervised or unsupervised learning which is
nowhere close to the power and complexity of intuitive reasoning by the human brain. However,
we may not also be able to throw away the idea of using computational tools to achieve better
results in the process of decision-making in legal argumentation. Even though we find the debate
by legal scholars very healthy, we believe that the formalism of legal language should not be the
point for contention, instead, the divergent ideas by legal scholars and logicians should be
converged, and as a matter of fact, the two positions of opinion augment each other. The
weakness of logic for legal reasoning presents the opportunities for assessing the structure of
4. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
14
legal language and constructing it to a form that allows for the use of logical tools; this brings us
to formalism and modelling of legal argumentation [27] which is able to capture isomorphism to
clarify the structure of legal reasoning.
3. CITIZENSHIP OF GHANA
There are several provisions by Ghanaian laws that give people access and outlines procedures
needed to acquire citizenship of Ghana. However, “along with the Constitution of Ghana, the
Citizenship Act (591) is the exhaustive law relating to citizenship in Ghana.”.The Act
consolidated amendments of other citizenship laws of Ghana, and provides for the determination
and acquisition of Citizenship of Ghana [28].
There are other relevant laws in addition to the nationality law which have effect on the access to
Ghanaian nationality; Registration of Births and Deaths Act, 1965, National Identity Register Act,
2008, Immigration Act, 2003, the Ghana Refugee Law, 1992. All these laws have established in
detail, how, when and where to attain different types of Ghanaian Citizenship (United Nations
High Commissioner for Refugees [29], [30].
The Citizenship Act (591) consolidates and categorises the various types of Ghanaian citizenship
into four parts. The first part describes existing citizenship by birth, which has been described by
different constitutions at and for different periods of time or date, which are not in contraventions
of each other. They are however put together in the Act (591) to establish all the conditions that
are valid to ascertain citizenship of Ghana depending on the time period a person was born.
The second part of the Act defines the acquisition of Ghanaian Citizenship other than by birth.
The laws of Ghana allows person of other nationalities to register to be citizen of Ghana or
naturalise as Ghanaians. The Act provides the various conditions a person has to satisfy to obtain
this type of citizenship of Ghana.
The third part of the Act is represented with three sections, that is, dual citizenship, renunciation
of citizenship and deprivation of citizenship. The last part of the Act outlines miscellaneous
provisions of the Act. This provides for all types of persons under different legal and natural
condition to be able to have access to Ghanaian citizenship.
The access to Ghanaian citizenship or nationality, and the proof of nationality are impacted by
institutions such as the Ministry of the Interior, Ghana Immigration Service, Ghana Refugee
Board Ministry of Foreign Affairs and Rational Integration, National Identification Authority,
Births and Deaths Registry, and the Ministry of Local Government and Rural Development [30],
[31].
4. RESULTS AND DISCUSSION
The modelled text of the Citizenship Act (591) of Ghana in this paper, is done to provide a
mechanism for analysing the semantics of the natural text of the Act. The logic model reveals the
difference in the semantic consequence on the choice and use of words between their natural and
logic form. The logic model of the text establishes a pattern of reasoning through the text,
contrasting all other possible wrong meaning that could be ascribed to the text either accidentally
or deliberately, due to the ambiguous use of some words in the text.
The text of the Act is constructed with logical connectives such as, if...then, or, and, and so forth.
It is important to note that, as a general rule, the literal meaning of these logical connectives in
natural language is always maintained in all logical use. The analysis made in this paper, reveals
5. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
15
the level of consistency between the semantics of the natural use of the logical connectives in the
Act, and their semantic implications in the logic model of the text.
4.1. FORMALISED TEXT OF THE ACT
We establish in this paper, that, the textual construction of the Act presents some level of inherent
ambiguities in its semantics. The use of some words in the internal structure of the statements
presents different meaning in their logical consequence. This kind of confusion does not seem to
be apparent in the natural use of the words. The logical consequence of the use of some words or
the style of sentence structure is only made picturesque in the formal model of the text.
Clarity of statements allows for comprehensibility and sound reasoning. If a statement is
comprehensible, it reduces the possibility of wrong conclusions to be derived from it. The
statements in the citizenship Act takes the form of antecedents and consequents; a structure that
allows for deductive reasoning. The formalised text in this paper is therefore done to preserve
clarity and comprehensibility of the text, and as well presents the text in a logic structure that
allows for deductive reasoning.
The logic formalism allows us to move through the propositions, systematically assessing the
truth state of each axiom during the process of reasoning in order to establish the semantics of the
whole statement. All consequents of the statements in the Act are derived from their antecedents
by means of the material implication, per the use of if..then conditionals in the Act. The
statements in the Act as well follow the semantic pattern of Γ ⊨ A, thus, for all set of premise that
makes Γ true, or that deduces Γ, also necessarily makes A true or deduces A, and it is therefore
impossible for a set of premise to be true and the semantic consequent to be false. This pattern is
enforced and maintained in the formalised text. If all necessary conditions for an argument is
established to be true then, its derived conclusion must be true.
4.1.1.CONTINUATION OF EXISTING CITIZENSHIP
The Section 1 of the Citizenship Act of Ghana states that “Every person who on the coming into
force of the Constitution was a citizen of Ghana by law shall continue to be a citizen of Ghana.”
Model:
∃lw, gh, T_eoc law(lw) ∧ country(gh) ∧ time(T_eoc) ∧ at(by(existing(Ctz(x, gh)), lw), T_eoc)
∀xcont(Ctz(x, gh)) ↔ at(by(existing(Ctz(x, gh)), lw), T_eoc)
In this model we have defined for any person xwho has continuous, cont, citizenship of
Ghana,gh;x should necessarily have had an existing citizenship of Ghana by law
by(existing(Ctz(x, gh)), lw), at the time of the enforcement of the constitution, T_eoc. This model
also connotes that, if a person has an existing citizenship of Ghana by law at the time of the
enforcement of the constitution, then the person can have continuous citizenship of Ghana.
The main challenge of the textual structure of the Section 1 of the Act is that, the statement is
presented in a long non-punctuated sentence, which makes it difficult for readers to determine the
scope of application of some of the entities in the text.
It is important to note that, the statements in the Act are declarative sentences and therefore holds
truth-values, and the consequents of the statements depend on the true meaning of the
antecedents, and not how it is being interpreted by readers, even though it is possible for an
unguided reader to infer any possible meaning to them.
6. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
16
There are several possible ways the Section 1could be contemplated, per the structure of the
sentence in the Act depending on how readers brake down the statement. We have placed sheffer-
strokes in the statement to make other ways of reading and reason through the text clearer.
Reasoning 1: Every person who on the coming into force of the Constitution was a citizen of
Ghana by law | shall continue to be a citizen of Ghana.
Reasoning 2: Every person who on the coming into force of the Constitution was a citizen of
Ghana by law | shall continue to be a citizen of Ghana.
Reasoning 3: Every person who on the coming into force of the Constitution was a citizen of
Ghana | by law shall continue to be a citizen of Ghana.
In the Reasoning one, every person in the universe was already a Citizen of Ghana by law, at the
time the constitution came into force. This way of reasoning through the statement presents
citizenship at a time t for every person x, and hence would produce the following model;∀x
person (x) → ∃t time(t) ∧ at(Ctz(x,gh), t).
However this is not the intent of the statement of the Act. Persons who already had Citizenship of
Ghana at the time the constitution came into force, are the persons being referred to, and not just
every person in the universe being citizen of Ghana at that particular time t. The model for this
statement however preserves its intended meaning, by presenting the statement as an atomic
proposition with defined arguments, which clarifies that all x being referred to are specific x that
have citizenship of Ghana by law, at time T_eoc, and these persons x are being referred to as
persons with existing citizenship, and only such persons can have continuous citizenship.
The text is also model to give a binding of the universal quantifier on persons x a narrow scope
with respect to the binding of the existential quantifier on the time and law entities;
∃T_eoc,lwhaving a wider scope over ∀x emphasises that, persons x can only have continuous
citizenship at the time T_eoc, which is a necessary condition for continuous citizenship. If the
model had presented ∀x to have a wider scope over ∃T_eoc,lw, that would have meant that, for
every person x there exists a time T_eoc and a law lw by which he or she can become citizen. This
scopal ambiguity is however resolved by the structure of model that is presented here.
The application of the term by law in the statement presents two different meanings the statement
in reasoning two and three, depending on how the term is applied or connected to the rest of the
sentence. The reasoning two suggests that, the persons were citizens of Ghana by law, while the
second suggests that, the persons were citizens of Ghana, but shall now continue to be citizens by
law. These two presentations of the same statement do not essentially carry the same meaning.
The application of the law shifts the whole meaning and intention of the statement.
The right model ∀x at(by(existing(Ctz(x, gh)), lw), T_eoc) ↔ cont(Ctz(x, gh)), however, is
constructed to enforce the application of every concept to objects in the statement by means of
defined predicates and their arguments. The axiom by(existing(Ctz(x, gh)), lw), clarifies that, at
time T_eoc,xmust be a citizen of Ghana by law in order to have continues citizenship.
We also establish that, formalism of the Section 1of the Act with a material implication may not
work well for some instance of its deductive reasoning. We assert the validity of the model per
the rules of material implication, the following is thus established;
• if a person satisfies at(by(existing(Ctz(x, gh)), lw), T_eoc), and such a person necessarily
satisfies cont(Ctz(x, gh)) as well, then the argument
∀x at(by(existing(Ctz(x, gh)), lw), T_eoc) → cont(Ctz(x, gh)) is valid.
7. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
17
• If a person does not satisfy at(by(existing(Ctz(x, gh)), lw), T_eoc), and as well does not
satisfy cont(Ctz(x, gh)), then, the argument is still valid.
• However, if a person does not satisfy at(by(existing(Ctz(x, gh)), lw), T_eoc), but satisfies
cont(Ctz(x, gh)), the argument will still remain valid; this is because, at(by(existing(Ctz(x,
gh)), lw), T_eoc) should not be the only proposition that should deduce cont(Ctz(x, gh))
according to the material conditional deduction rules. There should be other propositions
that should deduce cont(Ctz(x, gh)).
The challenge of the material implication in last assertion above is that, the definition of
continuous citizenship in the context of the Act is constructed to be a consequent of only persons
who already had citizenship at the time the constitutions came into force, that is, existing
citizenship. However, the text conditional provided in the Act does implements a unidirectional
material implication, which does not enforce the intended deduction of cont(Ctz(x, gh)) to be
based on only at(by(existing(Ctz(x, gh)), lw), T_eoc). So, even though the argument is valid for an
instance where x does not satisfy at(by(existing(Ctz(x, gh)), lw), T_eoc) but satisfies cont(Ctz(x,
gh)), changes the semantics consequence in the context of the Act. Emphatically, Persons who did
not have existing citizenship by law, at the time the constitution came into force, cannot have
continuous citizenship, and therefore should not be valid in the context of the Act as well as the
logical formalism.
We therefore denote that, a material bi-conditional implication resolves this problem (which is
not the way the statement was constructed in the Act), and maintains the semantics of the intent
of the Act, thus;
cont(Ctz(x, gh)) ↔ at(by(existing(Ctz(x, gh)), lw), T_eoc).
This is to say that, a person can have continuous citizenship, if and only if such a person satisfies
at(by(existing(Ctz(x, gh)), lw), T_eoc).
Therefore;
cont(Ctz(x, gh)) → at(by(existing(Ctz(x, gh)), lw), T_eoc)and
at(by(existing(Ctz(x, gh)), lw), T_eoc) → cont(Ctz(x, gh)).
The antecedent at(by(existing(Ctz(x, gh)), lw), T_eoc) therefore becomes a necessary and
sufficient condition for a person to have continuous citizenship.
Based on the bi-conditional implication, the argument cont(Ctz(x, gh)) ↔ at(by(existing(Ctz(x,
gh)), lw), T_eoc) is not valid for two instances elaborated in the validity check in the formp → q
and q → p. For;
P: cont(Ctz(x, gh)) → at(by(existing(Ctz(x, gh)), lw), T_eoc)
q: at(by(existing(Ctz(x, gh)), lw), T_eoc) → cont(Ctz(x, gh))
8. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
18
For every instance of x, at(by(existing(Ctz(x, gh)), lw), T_eoc) is necessary for cont(Ctz(x, gh)),
and cont(Ctz(x, gh)) is sufficient for at(by(existing(Ctz(x, gh)), lw), T_eoc). This satisfies the
intended semantic consequence of the natural statement in the citizenship Act. The logic structure
here emphasis that, a person must have existing citizenship before he or she can acquire
continuous citizenship of Ghana. This condition is however not made firm by the structure of
natural expression of the text in the Act. The logical implication expressed in the text of the Act
(which is an unintended outcome or misrepresentation by the use of textual implication) allows
for a person to have continuous citizenship without necessarily having an existing citizenship of
Ghana. The Act in converse seeks to establish that the, there are no other means of having
continuous citizenship except for the condition of having existing citizenship, which
unfortunately was misrepresented by the choice and use of material implication in the text.
One of the important factors that determine the semantics of a statement, is the entities in the
statements and how they relate with each other in the sentence structure. The true meaning of a
statement can be easily thrown off if the intended relations of the objects in the internal structure
of the statements are misplaced or misinterpreted. The literal intended meaning of statements of
the Act as well as their legal implications can be easily misinterpreted if a reader is not guided,
since that is one of the generic problems of natural language.
A logical construction of the statements in the Act required that, entities in the statements are
clearly identified, as well as establish how these entities relate. This can be very challenging,
because, some words are implied differently in the Act from their generic or lateral usage, which
creates the problem of ambiguities in the Act. We therefore establish through this model, that, a
material implication will not work for this piece of law when asserted logically. A bi-conditional
implication however provides adequate logical intention for the Section 1of the Act.
4.1.2. PERSONS BORN BEFORE 6/3/57
The Section 3 of the Act describes a citizenship type defined for persons born before the
independence of Ghana. This citizenship type is not based on any known law preceding the
independence of Ghana. It is however a citizenship by birth obtained by decent which is also a
legal means of attaining citizenship in Ghana even though we do not have any conditions defining
citizenship by decent in the Act.
According to the Act, there exists a time t which is the date of the independence of Ghana, such
that every person x born before that time born(x, before(t)) is citizen of Ghana by birth
byBirth(Ctz(x, gh)), but on the basis that the person should be born in Ghana born(x, in(gh)), and
at least one of his parents was born in Ghana born(p, in(gh)), or grandparent was born in Ghana
born(gp, in(gh)). The use of p for parent provides a variable for either mother or father, thus,
parent(p, x) → father(p, x) ∨ mother(p, x). The same is done with the use of gp as a variable for
9. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
19
any of the grandparents of x who is a parent of p, grandparent(gp, x) → parent(p, x) ∧ parent(pg,
p). The model is as follows;
∃t,x time(t) ∧ person (x) ∧ time(t)=03.06.57 ∧ born(x, before(t))
father(p, x) ∨ mother(p, x)
parent(p, x) → father(p, x) ∨ mother(p, x)
grandparent(gp, x) → parent(p, x) ∧ parent(gp, p)
∃p parent(p, x) ∧ born(p, in(gh))
∃gpgrandparent(gp, x) ∧ born(gp, in(gh))
∃t, p, gp time(t) = 03.06.57 ∧ born(x, in(gh)) ∧ born(x, before(t)) ∧ parent(p, x) ∧ grandparent(gp,
x) ∧ [born(p, in(gh)) ∨ born(gp, in(gh))] → byBirth(Ctz(x, gh))
∃p, parent(p, x) ∧¬ born(x, in(gh)) ∧ born(p, in(gh)) → byBirth(Ctz(x, gh))
Again we come across a very trick sentence structure in the Act that is open ended. In both
subsections, the model revealed that, the citizenship of any arbitrary x is dependent on only the
birth places of the parent or grandparent as external factors, and thus, born(p, in(gh)) ∨ born(gp,
in(gh)). Person x per these conditions derives citizenship from p and gp. The tricky aspect is that
the citizenship state of p and gp is not known within this piece of law.
The possible interpretations which introduces the twist to the semantics of this section is that, if
the condition born(p, in(gh)) ∨ born(gp, in(gh)) is satisfied, and p and gp do not have citizenship
of Ghana, x will still qualify to be citizen of Ghana as implied by this Section of the Act.
However, this may not work even for the literal inference for having citizenship of Ghana. That is
because, parents of x not being Ghanaian, irrespective of their citizenship, may as well mean that
such parents, through whom x drives citizenship from, may not originally be Ghanaians by birth.
If another variable y is introduced satisfying all the conditions of this Section 3 as child of x
whose citizenship is yet to be determined. Such a y will still qualify to be citizen of Ghana as long
as the birth place of x is Ghana, and this should not be the case even though that is how it is being
per the text of the Act. The model below is done to support the argument we have advanced on
Section 3 so far;
parent(x, y)
grandparent(gp, x)
∃t, ∀y time(t) ∧ person (y) ∧ time(t)=03.06.57 ∧
born(y, before(t))
∃gpgrandparent(gp, y) ∧ born(gp, in(gh))
∃t, p, gptime(t) = 03.06.57 ∧ born(y, in(gh)) ∧ born(y, before(t)) ∧ parent(x, y) → byBirth(Ctz(y,
gh))
In the model above, y derives citizenship from x who has already been defined in the previous
model as a person born in Ghana. By definition of the law, this is sufficient for y to be citizen of
Ghana, even though the citizenship of x is yet to be asserted. This presents a problem of inherent
fallacy in this Section of the law. That is because, it presents a situation of affirming a person to
be citizen by birth whose parents may not have citizenship of Ghana, which defies some rules of
obtaining citizen of Ghana.
The semantics of the natural presentation of this text can be resolved, if the relationship
established by the law between the antecedent and the consequent is more of causal relationship
than a logical deductive relationship. By this, we can say that, born(p, in(gh)) ∨ born(gp, in(gh))
is part of the system that causes x to be citizen of Ghana by birth, since it is considered relevant
by the constitution. This makes this type of citizenship of Ghana an empirical event other than a
logic condition.
10. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
20
The causal effect relationship in this piece of law rest on some qualitative theoretical
assumptions; the assumption that parents or grandparents of persons born in Ghana before the
independence of Ghana have citizenship of Ghana by decent. Even though stating this as an
axiom in a logical proposition works well, the possibilities of occurrences of such persons not
being Ghanaians will always result in a logical fallacy which is undesirable for any logic system.
The probabilistic cause of a parent or a grandparent born in Ghana but not Ghanaian will result
into x not being Ghanaian as well. As solution to the preserve the intended semantics in the Act,
this study presents the consequents of Section 3 of the Act as a causal effect of the antecedent
other than as logical effect. Thus;
P(¬ Ctz(x, gh) | ¬ [Ctz(p, gh) ∨Ctz(gp, gh)]).
4.1.3. PERSONS BORN ON OR AFTER 6/3/57 BUT BEFORE 22/8/69
The type citizenship by birth defined in the Section 4of the Actwas enforced by the first
parliamentary elections in Ghana, where we have two time periods that generally defines it; a
person x, born on or after 6th
March 1957which is the independence date of Ghana which we call
t1, thus, born(x, on(t1) ∨ born(x, after(t1)), and before 22nd
August 1969 which we call t2, thus,
born(x, before(t2)), qualifies to be citizen of Ghana by birth, if x was born in or outside Ghana;
this general qualifying criteria also depends on the birth place and citizenship status of the
parents, grandparents and/or great grandparents of x, all these criteria are asserted together to
determine this type of citizenship for x.
What is interesting in this part of the Act as a results of the logic model is that, the natural use of
the or disjunction implies that;x can be born on t1 only, born(x, on(t1)), or x can be born after
t1only,born(x, after(t1)), or, x can be born on t1and after t1 at the same time . However, it is not
possible in real sense for a person to be born on two different dates, as implied by the inclusive
use of the or disjunction in the statement. The use of either in the text would have enforced an
exclusionary application of the disjunction to maintain the intended logical semantics of the
statement. This study enforces the semantic intention of the statement, by the use of the exclusive
disjunction, which takes out the possibility of the occurrence of born(x,on(t1)) and born(x,
after(t1)) at the same time. The statement is therefore modelled as follows;
∃t1, t2time(t1)=03.06.57 ∧ time(t2)=22.08.69
∀x born(x, on(t1) ⨁ born(x, after(t1)) ∧ born(x, before(t2))
A person defined by the model above can be citizen of Ghana by birth if he or she satisfies either
of the two conditions in Section 4(1) of the Act. Section 4(1)(a) is specified for persons born in or
outside Ghana; the law requires that either of the parents of the person should be born in Ghana,
and at least a grandparent or great grandparent of the person should be born in Ghana.
Here again, the exclusive use of the disjunction either (used in the Act) for the parents of x being
born in Ghana, puts a twists on some parts of the semantics in the statement; either of the parents
of person x would mean that, either the mother or the father of x, and not both of them being born
in Ghana. By extension, x qualifies for citizenship of Ghana, if, only the mother of x was born in
Ghana, or if, only the father of x was born in Ghana. Person x however, is not qualified if both
mother and father are born in Ghana, according to the exclusionary use of the disjunctive either as
naturally expressed in the Act. This however, does not conform to the common sense of the law.
The inclusive use of the disjunction or in born([father(p, x) ∨ mother(p, x)], in(gh)), will rather
maintain the intended semantics of the statement. The inclusive use of the disjunction, would
imply that, both mother and father born in Ghana does not violate the ascertaining of citizenship
by person x. The model is as follows;
Persons born in Ghana:
11. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
21
father(p, x) ∨ mother(p, x)
parent(p, x) → father(p, x) ∨ mother(p, x)
grandparent(gp, x) → parent(p, x) ∧ parent(gp, p)
greatgrandparent (ggp, x) → grandparent(gp, x) ∧ parent(ggp, gp)
Therefore;
∃x,p, gp, ggp
parent(p, x)∧ grandparent(gp, x) ∧ greatgparent(ggp, x) ∧ born(x, in(gh)) ∧ born([father(p, x) ∨
mother(p, x)] , in(gh)) ∧ [born(gp, in(gh)) ∨ born(ggp, in(gh))]
Persons born outside Ghana:
∃x,p, gp, ggp
parent(p, x) ∧ grandparent(gp, x) ∧ greatgparent(ggp, x) ∧ ¬ born(x, in(gh)) ∧ born(p, in(gh)) ∧
[born(gp, in(gh)) ∨ born(ggp, in(gh))]
Therefore;
∀x [born(x, in(gh)) ⨁ ¬ born(x, in(gh))] ∧ [born(x, on(t1) ⨁ born(x, after(t1))] ∧ born(x,
before(t2))] → ∃p, gp, ggp parent(p, x) ∧ grandparent(gp, x) ∧ greatgparent(ggp, x) ∧
born([father(p, x) ∨ mother(p, x)] , in(gh)) ∧ [born(gp, in(gh)) ∨ born(ggp, in(gh))] →
byBirth(Ctz(x, gh))
∀x,∃p, gp born(x, in(gh)) ∧ parent(p, x) ∧ ¬ born(p, in(gh)) ∧ grandparent(gp, x) ∧ born(gp,
in(gh)) → byBirth(Ctz(x, gh))
The Section 4(2) of the Act defines person x to claim its citizenship through a parent,
claimedThrough(Ctz(x, gh), p), a grandparent, claimedThrough( Ctz(x, gh), gp), or great
grandparent claimedThrough( Ctz(x, gh), ggp). The law emphasises that, if p or gp or ggp through
whom x claims citizenship lose their citizenship at the time of birth of x, x will in effect not be
citizen of Ghana by birth.
∃p, gp, ggp
parent(p, x) ∧ grandparent(gp, x) ∧ greatgparent(ggp, x) ∧ [claimedThrough( Ctz(x, gh), p)
∨claimedThrough( Ctz(x, gh), gp) ∨claimedThrough( Ctz(x, gh), ggp) ] ∧ [at( ¬ Ctz(p, gh),
birth(x)) ∧ at( ¬ Ctz(gp, gh), birth(x)) ∧ at( ¬ Ctz(ggp, gh), birth(x))]→ ¬ Ctz(x, gh)
The Section 4(3) of the Act also emphasises the importance of p and gp having citizenship of
Ghana, and even the type of citizenship they must possess for x to be able to claim citizenship
through them, thus;
by(at([Ctz(father(p,x))∨Ctx(mother(p,x))],birth(x)),registration)⨁by(at([Ctz(father(p,x))
∨Ctx(mother(p,x))], birth(x)), naturalization).
The implication of the literal use of the disjunction in this section is problematic. A parent should
have citizenship of Ghana either by registration or naturalisation and not both type of citizenship
at the same time. The citizenship status of a parent that qualifies x can be the father or mother, or
both at same time. This is enforced by the right use of the disjunctive connectives in the model.
The Section 3(a) and 3(b) in the Act are the same but are separated as different conditions. The
difference lies in the use of both for persons born outside Ghana in Section 3(b) in place of either
for persons born in Ghana in Section 3(a). Hence, the first part of the statement is modeled as;
12. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
22
∃t1,t2 time(t1) ∧ time(t)=03.06.57 ∧ time(t2) ∧ time(t2)=22.08.69
∀x born(x, in(gh)) ∧ [born(x, on(t1) ⨁ born(x, after(t1))] ∧ born(x,
before(t2))] → ∃p father(p, x) ∨ mother(p, x) ∧ by(at( [Ctz(father(p,x)) ∨Ctz(mother(p,x))],
birth(x)), registration) ⨁ by(at([Ctz(father(p, x)) ∨Ctz(mother(p,x))], birth(x)), naturalization) →
byBirth(Ctz(x, gh))
The use of both is to emphasise that, one parent alone, whether mother or father being born in
Ghana does not form part of the qualifying criteria for persons born outside Ghana. Both parents
at least should be born in Ghana. The use of both therefore will function as conjunctive
connective in the statement.
∃t1,t2 time(t1) ∧ time(t)=03.06.57 ∧ time(t2) ∧ time(t2)=22.08.69
∀x born(x, in(gh)) ∧ [born(x, on(t1) ∨ born(x, after(t1))] ∧ born(x,
before(t2))] →∃p father(p, x) ∨ mother(p, x) ∧ by(at( [Ctz(father(p,x)) ∧Ctz(mother(p,x))],
birth(x)), registration) ⨁ by(at([Ctz(father(p, x)) ∧Ctz(mother(p,x))], birth(x)), naturalization) →
byBirth(Ctz(x, gh))
4.1.4. PERSONS BORN ON OR AFTER 22/8/69
The Section 5of the Act is defined for persons born on or after the date of enforcement of the
1960 constitution of Ghana. It follows the same definition as the previous section, but with a new
time stamp time(t3) =24.09.79, by which x has to be born at t2 in the previous section but before
t3. The parentp is also defined to have citizenship of Ghana. However, gp does not form part of
the criteria for x to claim citizenship, and this is because, p being citizen of Ghana remains
sufficient for x to claim citizenship through p without seeking to extend claim of citizenship
through gp. The citizenship of p however, should be valid at the time x was born, otherwise, x
will not be able to claim citizenship through p. This emphasises the importance of Citizenship of
p or gp having effect on the Citizenship of x, which is in converse description of ascertaining
citizenship in the Section 3 of the Act. The model for the Section 3 of the Act is as follows;
∃t3time(t3) =24.09.79
∀x [born(x, in(gh)) ⨁ ¬ born(x, in(gh)) ] ∧ [born(x, on(t2) ⨁ born(x, after(t2))] ∧ born(x,
before(t3))] → ∃p parent(p, x) ∧ [at( Ctz(p, gh), birth(x))] → byBirth(Ctz(x, gh)).
4.1.5. PERSONS BORN ON OR AFTER 24/9/79
Section 6 of the Act implements citizenship defined from the 1979 constitution of Ghana. The
citizenship of x is also the same as that of Section 5 of the Act, but with a time stamp of t4. Here
again, the definition states explicitly that p or gp should have citizenship of Ghana as a criteria for
x to claim his or her citizenship through them.
∃x,t4,p,gp born(x, in(gh)) ∧ time(t4)=07.01.93
∧ [born(x, on(t3)) ⨁ born(x, after(t3))] ∧ born(x, before(t4))]
∧parent(p, x)
∧grandparent(gp, x)
∧[ at( Ctz(father(p, x)), birth(x)) ∨ at( Ctz(mother(p, x)), birth(x))]
∨Ctz(grandparent(gp, x)), birth(x))
Sections 6(b) is similar to 6(a), but x can only claim citizenship through p in 6(a).
∃x,t4,p,gp ¬ born(x, in(gh)) ∧time(t4)=07.01.93
∧ [born(x, on(t3)) ⨁ born(x, after(t3))] ∧ born(x, before(t4))]
∧parent(p, x)
∧[ at( Ctz(father(p, x)), birth(x)) ∨ at( Ctz(mother(p, x)), birth(x))]
13. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
23
4.1.6. PERSONS BORN ON OR AFTER 7/1/93
The Section 7 of the Act provides that, a person is citizen of Ghana by birth if he or she is born on
or after the stipulated date in the provision, and at the time of his birth either [emphasis added] of
his parents was citizen of Ghana. Either of the parents of the person, to mean that, if only the
mother of the person was citizen of Ghana, or, if only the father of the person was citizen of
Ghana, but not both of them with citizenship of Ghana at the same time, according to the
exclusive use of the disjunctive either.
The disjunctive either in the Section 7 just as in the other sections might have not been intended
for its exclusive use, but it does however presents different logical consequence for the statements
it connects, this is because (as elaborated in the other sections) the default literal and structural
use either implies exclusivity.
∃t4time(5)=07.01.93
∀x born(x, in(gh)) ⨁ ¬born(x, in(gh))]
→ ∃t4, p, gpborn(x, on(t4) ∨ born(x, after(t4))]
∧parent(p, x)
∧grandparent(gp, x)
∧ [ at( [Ctz(father(p, x)) ∨Ctz(mother(p, x))], birth(x)) ∨ at( Ctz(gp, gh), birth(x))]
→ byBirth(Ctz(x, gh))
4.1.7. FOUNDLINGS
The Citizenship of a child x whose is found in Ghana, found(x, in(gh)) whose age is not more than
seven years, age(x) < 8, and whose parents are unknown ¬ known(p), is considered to be a
citizen of Ghana by default. This type of citizenship is based on some assumption and therefore
cannot be logically queried beyond the assumption.
∀x child(x) → ∃p, parent(p, x) ∧ age(x) < 8 ∧ found(x, in(gh)) ∧ ¬ known(p) → by Birht(Ctz(x,
gh))
The composition of some aspects of the law makes it challenging to process, especially for
proofing complete logical deductions. While some aspects present open-ended statements, others
are defined with limited logical provision.
Thus far, all the logical theorems provided in this study specifies or defines the various type of
criteria for a person to obtain citizenship of Ghana. Each level of definition is uniquely defined by
time stamps that determine the conditions that apply at the specified times. We will like to
emphasise that, each stage of the model defined by each section of the Act presents sufficient
premises for a person to be citizen of Ghana by birth.
Some of the interesting issues that are found in this discussion brings to bare other meanings
presented by the statements of the pieces of law through formalism, which is quite different from
the intention of the framing of the law, and reveal different semantics from the composition of the
text made in their literal use. The analysis done by this paper affirms the importance of words and
their meaning in legal statements which have always been debated in legal discourse in order to
ascertain the implication of statements in decision-making processes.
5. CONCLUSIONS
Researchers in computer science, specifically in AI, have provided some tools to deal with the
semantic problems in legal language, and are still generally seeking to provide improved versions
of tools that exist, as well as new ones that can present legal language in crisp logical form that
avoids confusion in the semantics of legal texts, as well as tools that can perform legal reasoning
14. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
24
in legal argumentation for precision in decision- making [31]. All of these converge to the fact
that “…it is a necessary condition for a judicial condition to be legally justified that it coheres
with some part of the established law” [32]; established law as a knowledge base to legal
processes and systems, and coherence to the law as system of deductive reasoning for decision-
making, which as yet remains a challenge, because there is no single robust logical system that
can deal with this difficulty entirely[33].
In this paper, we explored the possibility of having an entire established law as a logic theorem, a
form that generally revealed unintended or elusive semantic errors in natural expressions of the
text, and as well preserve a sound reasoning mechanism through the text. We chose to formalise
the Citizenship Act of Ghana which is a piece of law that presents technical and complex
interconnected facts, thought processes and various kinds of deductive reasoning in its
application. By this formalism, we have been able to semantically analyse the difference in the
logical sequences of words in their natural use in the Citizenship Act and establish logical
correctness in some aspects of the Act. Some of the interesting aspects in this formalism showed
that, the use of the material implication and the exclusive or inclusive use of disjunctions have
been particularly found in some cases not reflecting the logic intentions of the Act. The logic
models also presents the text of the Act in a form that removes or minimizes ambiguities and
establishes clarity for comprehensibility, and can as well serve as a deductive logic tool for the
augmentation of decision-making in legal systems.
ACKNOWLEDGEMENTS
We are grateful to the library department of the Supreme Court of Ghana for supporting us with
legal material and helping us understand some aspects of the Citizenship laws of Ghana.
REFERENCES
[1] T. Endicott (2016) “Law and Language” The Stanford Encyclopedia of Philosophy, accessed 5th
October 2018, from <http://plato.stanford.edu/archives/sum2016/entries/law-language/>
[2] J. Dickson (2010) “Interpretation and Coherence in Legal Reasoning” The
Stanford Encyclopedia of Philosophy, accessed 5th October 2018, from
<http://plato.stanford.edu/archives/sum2014/entries/legal-reas-interpret/>
[3] Aristotle (1955) “On Sophistical Refutations” Loch Classical Library, Cambridge, Mass., Harvard
University Press, accessed 5th October 2018, from
<http://www.hup.harvard.edu/catalog.php?isbn=9780674994416>
[4] D. N. Walton (1995) “A Pragmatic Theory Of Fallacy” University of Alabama Press.
[5] I. Witczak-Plisiecka (2007) “Language, law and speech acts: Pragmatic meaning in English legal
texts” Łódź: WyŜszaSzkołaStudiówMiędzynarodowych w Łodzi.
[6] B. H. Sandra (1984) “The discourse of court interpretations: Practice of the law, witness and the
interpreter”, John Benjamins Publishing Company.
[7] J. P. Butt, and C. Richard (2006) “Modern legal drafting: A guide to using clearer language” New
York: Cambridge University Press.
[8] A.B. Garner (2002) “The elements of legal style” New York: Oxford University Press.
[9] M. P. Tiersma (1999) “Legal language” Chicago: The University of Chicago Press.
[10] M. Asprey (2010) “ Plain Language for Lawyers,Federation Press.
[11] T. N. Hwee and Z. John (1997) “Corpus-Based Approaches to Semantic Interpretation in Natural
Language Processing” The American Association for Artificial Intelligence Magazine, Vol. 18, No. 4.
[12] R. S. Trehan (2014) “An “Unfortunate Bit of Legal Jargon”; Prosecutorial Vouching Applied to
Cooperating witness” Columbia Law Review Association Inc, Vol. 114, No. 4, pp997-1032.
15. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
25
[13] F. Michael and S. Fiona (2013) “Law and Language” Oxford University Press, Vol 15.
[14] A. Wagner and S. Cacciaguidi-Fahy (2006) “Legal Language and the search for Clarity: Practice and
tools”,Peter Langi.
[15] C. William (2006) “Fuzziness in Legal English: what shall we do with ‘shall’?,” Peter Lang.
[16] T. Bell (2018) “what is Natural Language Processing? The Business benefits of NLP Explained” CIO
from IDG,accessed 5th October 2018,from<https://www.cio.com/article/3258837/artificial-
intelligence/what-is-natural-language-processing-the-business-benefits-of-nlp-explained.html>
[17] R. Mihalcea, H. Liu and H. Lieberman (2006) “NLP (Natural Language Processing) for NLP (Natural
Language Programming)” in Gelbukh A. (eds) Computational Linguistics and Intelligent Text
Processing. CICLing 2006. Lecture Notes in Computer Science, Vol. 3878. Springer, Berlin,
Heidelberg.
[18] Grau, Harrock, Motik, Parsia, Patel-Schneider and Sattler (2008) “OWL2: The Next Step for OWL”
University of Oxford, United Kingdom.
[19] A. Horn (1951) “On sentences which are true of direct union of algebras” Journal of Symbolic Logic,
vol. 16, No. 1, pp14-21.
[20] P. B. Andrews (2002) “An Introduction to Mathematical Logic and Type Theory: To Truth Through
Proof”Kluwer Academic Publishers, Springer.
[21] P. K. Pandya, (2005) “Monadic Second-Order Logic; Automata and Practice” University of Trento,
TIFR, Mumbai, India, pp10-24.
[22] N. Bidoit and R. Hull (1989) “Minimalism, justification and non-monotonicity in deductive
databases” Journal of Computer and System Sciences, Vol. 38, pp 290-325.
[23] B. Verheij, J. Hage, and A. R. Lodder (1997) “Logical tools for legal argument: a practical assessment
in the domain of tort” Dissertation UniversiteitMaastricht, accessed 7th August 2018, from
<http://pub.maastrichtuniversity.nl/d2a53c49-d176-41a8-a5c1-8e9234c62021>
[24] L. O. Kelso, (1946)“Does the law need a technological revolution?”Rocky Mountain Law Review,
Vol. 18, pp378–392.
[25] N. Love and M. Genesereth (2005) “Computational Law”. ICAIL ’05, ACM, 1-59593-081, Bologna,
Italy, June 6-11, 2005.
[26] M. K. Anjali and P.A. Babu (2014) “Ambiguities in Natural Language Processing” International
Journal of Innovative Research in Computer and Communication Engineering. Vol. 2, No. 5.
[27] G. Sator (19194) “A Formal model of Legal Argumentation” International Journal of Jurisprudence
and Philosophy of Law.
[28] Wikipedia (2018) “Ghanaian Nationality Law”, accessed 14th June 2018, from
<https://en.wikipedia.org/wiki/Ghanaian_nationality_law>
[29] United Nations High Commissioner for Refugees (UNHCR) (2016). Terms of Reference: Study on
Statelessness in Ghana, Accra, Ghana
[30] UN High Commissioner for Refugees (UNHCR), UNHCR& IOM, Nationality, Migration and
Statelessness in West Africa (2015), accessed 22nd August 2018, from
<http://www.refworld.org/docid/55b886154.html>
[31] L. Al-Abdulkarim, K. Atkinson and T. J. M. Bench-Capon (2016) “A methodology for designing
systems to reason with legal cases using Abstract Dialectical Frameworks” Artificial Intelligence and
Law, Vol. 24, No. 1,pp1-49.
[32] B. B. Levenbook (1984) “The Role of Coherence in Legal Reasoning” Law andPhilosophy,Vol. 13,
pp355–74.
[33] A. Gibson, G. Rowe and C. Reed (2007) “A Computational Approach to Identifying Formal Fallacy”.
Paper presented at Working Notes of the 7th Workshop on Computational Models of Natural
Argument, CMNA 2007, pp26–30.
16. International Journal on Natural Language Computing (IJNLC) Vol.7, No.5, October 2018
26
AUTHORS
Callistus Ireneous Nakpih is a lecturer at the St. John Bosco’s College of Education in
Ghana. He has functioned as head of some academic departments in the College of which
the Quality Assurance Department is the latest. He is currently playing a national role in
the development and integration of ICT policies into education in Ghana, as well as in the
development of a new curriculum for pre-tertiary education in Ghana. As a researcher, he
is interested in Artificial Intelligences especially in Natural Language Processing and is
willing to explore in research not only to add to knowledge but to also advance the
Computational development in Ghana.