SlideShare a Scribd company logo
1 of 38
Natural Language Processing
(CS735E01) – 7th Semester
Mithun B N
Asst. Prof
Unit 1:
Introduction to
Natural Language Processing
Agenda
• The Study of language
• Applications of Natural language understanding
• Evaluating Language understanding system
• The different levels of language analysis
• Representation and Understanding
The study of Language
• Language is on the fundamental aspects of human behaviour.
• It is a crucial component of our lives.
• It could be written or spoken form:
• Written form would serve as long term record for knowledge from one
generation to the next.
• Spoken form serves as our primary means of coordinating our day-to-day
behaviour with others.
The study of Language (Contd.,) Goals of NLP research
• Create computational models of language
• Able to specify models that approach human performance in the
linguistic tasks.
• Linguistic tasks are: reading, writing, hearing and speaking.
• Computational model are useful for scientific and practical purposes
• Scientific purpose – nature of linguistic communication
• Practical purpose – enabling effective human machine interaction
The study of Language (Contd.,)
Different academic disciplines
• The linguist – structure of the language
• The Philosopher – how words mean anything at all and not
• The Psycholinguists – process of human language production and
comprehension
• The Computational Linguists – computational theory of language
Applications of Natural Language Processing
•Text based application
•Dialogue based application
Text Based Applications
• Processing of written text – books, newspapers, reports, manuals,
email messages and so on.
• Finding appropriate documents on certain topics from database of
texts
• Extracting information from messages or articles on certain topics
• Translating documents from one language to another
• Summarizing texts for certain purposes
Text Based Applications (Contd.,)
• All may not use NLP, articles can be retrieved by simple matching
technique.
• Machine translation systems built on pattern matching - fails as it is
inability to use an understanding of content to disambiguate word
senses and sentence meanings
• Instead, produce a representation of meaning of each sentence in
one language and then producing a sentence in the other language
that realizes the same meaning
Dialogue Based applications
• Involve human machine communication
• Question-answering systems, where natural language is used to query
a database
• Automated customer service over the telephone
• Tutoring systems, where the maching interacts with a student
• Spoken language control of the machine
• General cooperative problem solving system
• Important to distinguish the problems of speech recognition from the
problems of language understanding
A Dialogue with Eliza
User ELIZA
Men are all alike In what way?
They are always bugging us about something or
other
Can you think of a specific example?
Well, my boy friend made me come here Your boy friend made you come here
He says I am depresses much of the time I am sorry to hear you are depressed
It’s true, I am unhappy Do you think coming here will help you not to be
unhappy?
I need some help that much seems certain What would it mean to you if you got some help
Perhaps I could learn to get along with my mother Tell me more about your family
My mother takes care of me Who else in your family takes care of you?
My father Your father
You are like my father in some ways What resemblance do you see?
The Different Levels of Language Analysis
• Considerable knowledge about the structure of the language
• what words are, how words are combined to sentences, their meaning.
Different forms of knowledge relevant for NLP:
• Phonetic and phonological knowledge: how words are related to
sounds
• Morphological Knowledge: how words are constructed from
more basic meaning units called morphemes (primitive unit of
meaning in a language)
• Syntactic knowledge: how words can be put together to form
correct sentences and structural roles
• Semantic knowledge: what words mean and how these
meanings combine in sentences to form sentence meanings
• Pragmatic knowledge: concerns how sentence are used in
different situations and it affects interpretation of the
sentence.
• Discourse Knowledge: concerns how the immediately preceding
sentence affect the interpretation of the next sentence.
• World knowledge: includes the general knowledge about the
structure of the world that language users must have in order to.
The Different Levels of Language Analysis
Example: syntax, semantics and pragmatics
1. Language is one of the fundamental aspects of human behaviour
and is a crucial component of our lives
2. Green frogs have large noses
3. Green ideas have large noses
4. Large have green ideas nose.
Sentence 1 is reasonable; has syntax semantics and pragmatics.
Sentence 2 is well formed syntactically and semantically but not
pragmatically.
Sentence 3 is semantically and pragmatically ill formed.
Sentence 4 is unintelligible
If I ask you where are you going and you reply – “ I go store”
Response is understandable, syntactically ill
Representation and Understanding
• Most words have multiple meanings – called as senses.
• Cook – has a sense as a verb and a sense as a noun
• Dish – as a noun and as a verb
• Useful representation languages have two properties:
• representation must be precise and unambiguous.
• representation should capture intutitive structure of the NL sentences that it
represents
Representation and Understanding: Syntax –
Representing Sentence Structure
• Syntactic structure of a sentence indicates the way that words in the
sentence are related to each other.
• NLP should be able to understand ill-formed sentences.
• Example:
• John sold the book to mary
• The book was sold to mary by john
• *After it fell in the river, John sold Mary the book.
• After it fell in the river, the book was sold to mary by john
• *John are in the corner
• *John put the book
Representation and Understanding: Syntax –
Representing Sentence Structure
• Flying planes are dangerous
• Flying planes is dangerous
Languages are based on the notion of CFG, representing sentence
structure in terms of what phrases are subpars of other phrases.
Representation and Understanding: The
Logical Form
• The structure of a sentence doen’t reflect its meaning.
• The intended meaning of a sentence depends on the situation in
which the sentence is produced.
• Context dependent meaning and context independent meaning.
• The representation of the context independent meeing of a sentence
is called its logical form.
Jack invited Mary to the Halloween ball.
The Organization of Natural Language Understanding
• Syntactic structure and logical form is called as Parser
• Is uses knowledge about word and word meanings (the lexicon) and a
set of rules defining the legal structures (the grammar) in order to
assign a syntactic structure and logical form to an input sentence
• Visiting relatives can be trying
• Visiting museums can be trying
• Above two sentences have identical syntactic structure, and are
syntactically ambiguous
• First sentence might be relatives who are visiting you or the event of you
visiting relatives
• Both of these alternatives are semantically valid and you would need to
determine the appropriate sense by using the contextual mechanism
• Second sentence has only one possible semantic interpretation, since
museums are not objects that can visit other people, rather they must be
visited.
• If syntactic and semantic processing are combined the system will be
able to detect the semantic anomaly as soon as it interprets the phrase
visiting museums
• The grammar that can be used to identify the structure of a given
sentence or to realize a structure of words is called as bidirectional
grammar
Linguistic Background: An Outline of English Syntax
Words:
• Word – basic unit of linguistic structure.
• Morphology – concerns the construction of words from more basic
components.
• Two ways of forming words:
• Inflectional – use a root from of a word and add suffix to make appropriate
form. Verbs are the best example: give gives giving given (shares same
basic meaning.
• Derivational – derivation of new words from other forms. New words may be
completely different categories. Friend friendly friendliness
Words (Contd.,)
• Traditionally words are classified into different categories based on
their uses.
• First – word’s contribution to the meaning of the phrase that contains it
• Second – the actual syntactic structure in which the word play a role
• Noun and Adjective
• Noun – identify the basic type of object
• Adjective – qualify the object, concept of place
• The green book. Green books
• That green is lighter than the other
• Modifiers can be noun modifier and adjective modifier.
• Four main classes of words
• Nouns
• Verbs
• Adjectives
• Adverbs
• Other classes
• Articles
• Pronouns
• Prepositions
• Particles
• Quantifiers
• Conjunctions and so on.
Words (Contd.,)
• Head of the Phrase: A word in any of four open classes:
• Noun Phrase:
• The elephant
• An elderly elephant
• The angry elephant killed two men
• Adjective Phrase
• Thirsty
• Very thirsty
• Thirsty made him to do so
Words (Contd.,)
• Sometimes head requires additional phrases following it to express
the desired meaning.
• Example: ‘put’ cannot form a verb phrase in isolation.
• John put - cannot be a sentence.
• Instead, john put dog in the house.
• Sentence can be completed using complement
• The phrase or set of phrases needed to complete the meaning of
head is called the complement.
• In the above example, house is complement.
Words (Contd.,)
Noun Phrases Verb Phrases
The president of the company Looked up the chimney
His desire to succeed Believed that the world was flat
Several challenges from the opposing
team
Ate the pizza
Adjective Phrases Adverbial Phrases
It is easy to assemble Rapidly like a bat
I am happy that he won the prize Intermittently throughout the day
He is angry as a hippo Inside the house
Words (Contd.,)
The elements of simple noun phrases
• Noun phrases (NPs) are used to refer to things: objects, places,
concepts, events, qualities and so on.
• The simplest NP consists of a single pronoun. Pronouns can refer to
physical objects, to objects, to qualities and sometimes takes any
modifiers.
• It hid under the rug
• Once I opened the door, I regretted it for months
• He was so angry, but he didn’t show it.
• He who hesitates is lost. (pronouns taking modifiers very rarely)
• Proper noun is also used.
• Head of noun phrase is usually a common noun.
• Nouns divide into two main classes:
• Count nouns – describe specific objects or sets of objects
• Mass nouns – describe composites or substances
• Noun phrase may contain specifiers and qualifiers preceding the
head.
• Qualifiers describe the general class of objects identified by the head.
• Specifiers describe how many such objects are described.
The elements of simple noun phrases
• Specifiers are constructed out of
• Ordinals like first and second
• Cardinals like one and two
• Determiners
• Determiners has following divisions
• Articles – a, an and the.
• Demonstratives – this, that, these and those.
• Possessives – noun phrases followed by the suffix ‘s. Ajay’s . Possessive
pronouns are her, my and whose.
• Wh-determiners – words used in questions, which and what.
• Quantifying determiners – some, every, most so, any, both and half.
The elements of simple noun phrases
• A simple noun phrase may have at most one determiner, one ordinal and
one cardinal.
• A sentence may have all three – first three contestants.
• Sentence may contain few quantifying determiners – few songs we knew
• The qualifiers in a noun phrase occur after the specifiers (if any) and before
the head. They consist of adjectives and nouns being used as modifiers.
• Adjectives – words that attribute qualities to objects yet do not refer to the qualities
themselves. Angry is an adjective that attributes the quality of anger to something
• Noun modifiers – mass or count nouns used to modify another noun. Cook book or
the ceiling paint can.
The elements of simple noun phrases
• Pronouns take forms based on :
• Person – first, second and third.
• Gender – masculine, feminine and neutral.
• In some languages nouns are classified by their gender (French)
• Pronouns distinguish number, person, gender and case (possessive,
subject or object)
The elements of simple noun phrases
Number First person Second person Third person
Singular I You He, she it
Plural We You they
The elements of simple noun phrases
Number First person Second person Third person
Singular My Your His, her, its
Plural our Your Their
Pronouns as subject
Pronouns possessiveness
Number First person Second person Third person
Singular Me You Him, her, it
Plural us you them
• A sentence is used to assert, query or command.
• Mood – The way a sentence is used
Verb Phrases and Simple sentences
Mood Example
Declarative or assertion The cat is sleeping
Yes/no question Is the cat sleeping?
Wh-question What is sleeping? Or which cat is
sleeping?
Imperative (or command) Shoot the cat!
• Verbs can be divided into several different classes:
• The auxiliary verbs – be, do and have
• The modal verbs – will, can and could
• The main verbs – eat, ran and believe
Verb Phrases and Simple sentences
Natural Language Processing - Unit 1

More Related Content

What's hot

Natural language processing
Natural language processing Natural language processing
Natural language processing Md.Sumon Sarder
 
Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)Alia Hamwi
 
Basic techniques in nlp
Basic techniques in nlpBasic techniques in nlp
Basic techniques in nlpSumit Sony
 
natural language processing help at myassignmenthelp.net
natural language processing  help at myassignmenthelp.netnatural language processing  help at myassignmenthelp.net
natural language processing help at myassignmenthelp.netwww.myassignmenthelp.net
 
Natural Language Processing seminar review
Natural Language Processing seminar review Natural Language Processing seminar review
Natural Language Processing seminar review Jayneel Vora
 
Challenges in nlp
Challenges in nlpChallenges in nlp
Challenges in nlpZareen Syed
 
NLP_KASHK:Finite-State Morphological Parsing
NLP_KASHK:Finite-State Morphological ParsingNLP_KASHK:Finite-State Morphological Parsing
NLP_KASHK:Finite-State Morphological ParsingHemantha Kulathilake
 
Natural language processing
Natural language processingNatural language processing
Natural language processingAbash shah
 
Natural language processing
Natural language processingNatural language processing
Natural language processingBasha Chand
 
Natural Language Processing in AI
Natural Language Processing in AINatural Language Processing in AI
Natural Language Processing in AISaurav Shrestha
 
Natural language-processing
Natural language-processingNatural language-processing
Natural language-processingHareem Naz
 
Natural language processing
Natural language processingNatural language processing
Natural language processingSaurav Aryal
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language ProcessingVeenaSKumar2
 
Object oriented testing
Object oriented testingObject oriented testing
Object oriented testingHaris Jamil
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language ProcessingRishikese MR
 

What's hot (20)

Natural language processing
Natural language processing Natural language processing
Natural language processing
 
Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)
 
Basic techniques in nlp
Basic techniques in nlpBasic techniques in nlp
Basic techniques in nlp
 
natural language processing help at myassignmenthelp.net
natural language processing  help at myassignmenthelp.netnatural language processing  help at myassignmenthelp.net
natural language processing help at myassignmenthelp.net
 
Natural Language Processing seminar review
Natural Language Processing seminar review Natural Language Processing seminar review
Natural Language Processing seminar review
 
Challenges in nlp
Challenges in nlpChallenges in nlp
Challenges in nlp
 
Natural language processing
Natural language processingNatural language processing
Natural language processing
 
NLP_KASHK:Finite-State Morphological Parsing
NLP_KASHK:Finite-State Morphological ParsingNLP_KASHK:Finite-State Morphological Parsing
NLP_KASHK:Finite-State Morphological Parsing
 
NLP
NLPNLP
NLP
 
Natural language processing
Natural language processingNatural language processing
Natural language processing
 
Nlp
NlpNlp
Nlp
 
Natural language processing
Natural language processingNatural language processing
Natural language processing
 
Natural Language Processing in AI
Natural Language Processing in AINatural Language Processing in AI
Natural Language Processing in AI
 
Natural language-processing
Natural language-processingNatural language-processing
Natural language-processing
 
Natural language processing
Natural language processingNatural language processing
Natural language processing
 
1 Introduction.ppt
1 Introduction.ppt1 Introduction.ppt
1 Introduction.ppt
 
Treebank annotation
Treebank annotationTreebank annotation
Treebank annotation
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 
Object oriented testing
Object oriented testingObject oriented testing
Object oriented testing
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 

Similar to Natural Language Processing - Unit 1

HLLT 021 pp Presentation1 2019.pptx
HLLT 021  pp Presentation1  2019.pptxHLLT 021  pp Presentation1  2019.pptx
HLLT 021 pp Presentation1 2019.pptxMaripaneJT1
 
Critical discourse analysis
Critical discourse analysisCritical discourse analysis
Critical discourse analysisayeshahussain47
 
Syntax and lexis presentation final 3
Syntax and lexis presentation final 3Syntax and lexis presentation final 3
Syntax and lexis presentation final 3mohamed oubedda
 
Syntax and lexis presentation final 3
Syntax and lexis presentation final 3Syntax and lexis presentation final 3
Syntax and lexis presentation final 3mohamed oubedda
 
Linguistics notes 1
Linguistics notes 1Linguistics notes 1
Linguistics notes 1h4976
 
Systemic Functional Linguistics
Systemic Functional LinguisticsSystemic Functional Linguistics
Systemic Functional LinguisticsLaiba Yaseen
 
Linguistics - Dr.Chithra G.K (Associate Professor at VIT)
Linguistics - Dr.Chithra G.K  (Associate Professor at VIT)Linguistics - Dr.Chithra G.K  (Associate Professor at VIT)
Linguistics - Dr.Chithra G.K (Associate Professor at VIT)DrChithraGK
 
1. level of language study.pptx
1. level of language study.pptx1. level of language study.pptx
1. level of language study.pptxAlkadumiHamletto
 
01-Intro.pdf
01-Intro.pdf01-Intro.pdf
01-Intro.pdfyesufali2
 
Properties of language
Properties of languageProperties of language
Properties of languageAmnaAkbar12
 
Natural Language Processing (NLP).pptx
Natural Language Processing (NLP).pptxNatural Language Processing (NLP).pptx
Natural Language Processing (NLP).pptxSHIBDASDUTTA
 
Lecture 1st-Introduction to Discourse Analysis._023928.pptx
Lecture 1st-Introduction to Discourse Analysis._023928.pptxLecture 1st-Introduction to Discourse Analysis._023928.pptx
Lecture 1st-Introduction to Discourse Analysis._023928.pptxGoogle
 
Linguistics definition and its branches.PPTX
Linguistics definition and its branches.PPTXLinguistics definition and its branches.PPTX
Linguistics definition and its branches.PPTXashraf7897
 
Transformational grammar
Transformational grammarTransformational grammar
Transformational grammarJack Feng
 

Similar to Natural Language Processing - Unit 1 (20)

HLLT 021 pp Presentation1 2019.pptx
HLLT 021  pp Presentation1  2019.pptxHLLT 021  pp Presentation1  2019.pptx
HLLT 021 pp Presentation1 2019.pptx
 
Critical discourse analysis
Critical discourse analysisCritical discourse analysis
Critical discourse analysis
 
Syntax and lexis presentation final 3
Syntax and lexis presentation final 3Syntax and lexis presentation final 3
Syntax and lexis presentation final 3
 
Syntax and lexis presentation final 3
Syntax and lexis presentation final 3Syntax and lexis presentation final 3
Syntax and lexis presentation final 3
 
Lesson 40
Lesson 40Lesson 40
Lesson 40
 
AI Lesson 40
AI Lesson 40AI Lesson 40
AI Lesson 40
 
Word meaning
Word meaning Word meaning
Word meaning
 
Linguistics notes 1
Linguistics notes 1Linguistics notes 1
Linguistics notes 1
 
01 intro
01 intro01 intro
01 intro
 
Systemic Functional Linguistics
Systemic Functional LinguisticsSystemic Functional Linguistics
Systemic Functional Linguistics
 
L1 nlp intro
L1 nlp introL1 nlp intro
L1 nlp intro
 
3.pptx
3.pptx3.pptx
3.pptx
 
Linguistics - Dr.Chithra G.K (Associate Professor at VIT)
Linguistics - Dr.Chithra G.K  (Associate Professor at VIT)Linguistics - Dr.Chithra G.K  (Associate Professor at VIT)
Linguistics - Dr.Chithra G.K (Associate Professor at VIT)
 
1. level of language study.pptx
1. level of language study.pptx1. level of language study.pptx
1. level of language study.pptx
 
01-Intro.pdf
01-Intro.pdf01-Intro.pdf
01-Intro.pdf
 
Properties of language
Properties of languageProperties of language
Properties of language
 
Natural Language Processing (NLP).pptx
Natural Language Processing (NLP).pptxNatural Language Processing (NLP).pptx
Natural Language Processing (NLP).pptx
 
Lecture 1st-Introduction to Discourse Analysis._023928.pptx
Lecture 1st-Introduction to Discourse Analysis._023928.pptxLecture 1st-Introduction to Discourse Analysis._023928.pptx
Lecture 1st-Introduction to Discourse Analysis._023928.pptx
 
Linguistics definition and its branches.PPTX
Linguistics definition and its branches.PPTXLinguistics definition and its branches.PPTX
Linguistics definition and its branches.PPTX
 
Transformational grammar
Transformational grammarTransformational grammar
Transformational grammar
 

Recently uploaded

247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).pptssuser5c9d4b1
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130Suhani Kapoor
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Dr.Costas Sachpazis
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlysanyuktamishra911
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...Soham Mondal
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordAsst.prof M.Gokilavani
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxupamatechverse
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxpranjaldaimarysona
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxAsutosh Ranjan
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...ranjana rawat
 
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 

Recently uploaded (20)

247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptx
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
 
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
 

Natural Language Processing - Unit 1

  • 1. Natural Language Processing (CS735E01) – 7th Semester Mithun B N Asst. Prof
  • 2. Unit 1: Introduction to Natural Language Processing
  • 3.
  • 4. Agenda • The Study of language • Applications of Natural language understanding • Evaluating Language understanding system • The different levels of language analysis • Representation and Understanding
  • 5. The study of Language • Language is on the fundamental aspects of human behaviour. • It is a crucial component of our lives. • It could be written or spoken form: • Written form would serve as long term record for knowledge from one generation to the next. • Spoken form serves as our primary means of coordinating our day-to-day behaviour with others.
  • 6. The study of Language (Contd.,) Goals of NLP research • Create computational models of language • Able to specify models that approach human performance in the linguistic tasks. • Linguistic tasks are: reading, writing, hearing and speaking. • Computational model are useful for scientific and practical purposes • Scientific purpose – nature of linguistic communication • Practical purpose – enabling effective human machine interaction
  • 7. The study of Language (Contd.,) Different academic disciplines • The linguist – structure of the language • The Philosopher – how words mean anything at all and not • The Psycholinguists – process of human language production and comprehension • The Computational Linguists – computational theory of language
  • 8. Applications of Natural Language Processing •Text based application •Dialogue based application
  • 9. Text Based Applications • Processing of written text – books, newspapers, reports, manuals, email messages and so on. • Finding appropriate documents on certain topics from database of texts • Extracting information from messages or articles on certain topics • Translating documents from one language to another • Summarizing texts for certain purposes
  • 10. Text Based Applications (Contd.,) • All may not use NLP, articles can be retrieved by simple matching technique. • Machine translation systems built on pattern matching - fails as it is inability to use an understanding of content to disambiguate word senses and sentence meanings • Instead, produce a representation of meaning of each sentence in one language and then producing a sentence in the other language that realizes the same meaning
  • 11. Dialogue Based applications • Involve human machine communication • Question-answering systems, where natural language is used to query a database • Automated customer service over the telephone • Tutoring systems, where the maching interacts with a student • Spoken language control of the machine • General cooperative problem solving system • Important to distinguish the problems of speech recognition from the problems of language understanding
  • 12. A Dialogue with Eliza User ELIZA Men are all alike In what way? They are always bugging us about something or other Can you think of a specific example? Well, my boy friend made me come here Your boy friend made you come here He says I am depresses much of the time I am sorry to hear you are depressed It’s true, I am unhappy Do you think coming here will help you not to be unhappy? I need some help that much seems certain What would it mean to you if you got some help Perhaps I could learn to get along with my mother Tell me more about your family My mother takes care of me Who else in your family takes care of you? My father Your father You are like my father in some ways What resemblance do you see?
  • 13. The Different Levels of Language Analysis • Considerable knowledge about the structure of the language • what words are, how words are combined to sentences, their meaning. Different forms of knowledge relevant for NLP: • Phonetic and phonological knowledge: how words are related to sounds • Morphological Knowledge: how words are constructed from more basic meaning units called morphemes (primitive unit of meaning in a language) • Syntactic knowledge: how words can be put together to form correct sentences and structural roles • Semantic knowledge: what words mean and how these meanings combine in sentences to form sentence meanings
  • 14. • Pragmatic knowledge: concerns how sentence are used in different situations and it affects interpretation of the sentence. • Discourse Knowledge: concerns how the immediately preceding sentence affect the interpretation of the next sentence. • World knowledge: includes the general knowledge about the structure of the world that language users must have in order to. The Different Levels of Language Analysis
  • 15. Example: syntax, semantics and pragmatics 1. Language is one of the fundamental aspects of human behaviour and is a crucial component of our lives 2. Green frogs have large noses 3. Green ideas have large noses 4. Large have green ideas nose. Sentence 1 is reasonable; has syntax semantics and pragmatics. Sentence 2 is well formed syntactically and semantically but not pragmatically. Sentence 3 is semantically and pragmatically ill formed. Sentence 4 is unintelligible If I ask you where are you going and you reply – “ I go store” Response is understandable, syntactically ill
  • 16. Representation and Understanding • Most words have multiple meanings – called as senses. • Cook – has a sense as a verb and a sense as a noun • Dish – as a noun and as a verb • Useful representation languages have two properties: • representation must be precise and unambiguous. • representation should capture intutitive structure of the NL sentences that it represents
  • 17. Representation and Understanding: Syntax – Representing Sentence Structure • Syntactic structure of a sentence indicates the way that words in the sentence are related to each other. • NLP should be able to understand ill-formed sentences. • Example: • John sold the book to mary • The book was sold to mary by john • *After it fell in the river, John sold Mary the book. • After it fell in the river, the book was sold to mary by john • *John are in the corner • *John put the book
  • 18. Representation and Understanding: Syntax – Representing Sentence Structure • Flying planes are dangerous • Flying planes is dangerous Languages are based on the notion of CFG, representing sentence structure in terms of what phrases are subpars of other phrases.
  • 19.
  • 20. Representation and Understanding: The Logical Form • The structure of a sentence doen’t reflect its meaning. • The intended meaning of a sentence depends on the situation in which the sentence is produced. • Context dependent meaning and context independent meaning. • The representation of the context independent meeing of a sentence is called its logical form. Jack invited Mary to the Halloween ball.
  • 21. The Organization of Natural Language Understanding • Syntactic structure and logical form is called as Parser • Is uses knowledge about word and word meanings (the lexicon) and a set of rules defining the legal structures (the grammar) in order to assign a syntactic structure and logical form to an input sentence • Visiting relatives can be trying • Visiting museums can be trying • Above two sentences have identical syntactic structure, and are syntactically ambiguous
  • 22. • First sentence might be relatives who are visiting you or the event of you visiting relatives • Both of these alternatives are semantically valid and you would need to determine the appropriate sense by using the contextual mechanism • Second sentence has only one possible semantic interpretation, since museums are not objects that can visit other people, rather they must be visited. • If syntactic and semantic processing are combined the system will be able to detect the semantic anomaly as soon as it interprets the phrase visiting museums • The grammar that can be used to identify the structure of a given sentence or to realize a structure of words is called as bidirectional grammar
  • 23.
  • 24. Linguistic Background: An Outline of English Syntax Words: • Word – basic unit of linguistic structure. • Morphology – concerns the construction of words from more basic components. • Two ways of forming words: • Inflectional – use a root from of a word and add suffix to make appropriate form. Verbs are the best example: give gives giving given (shares same basic meaning. • Derivational – derivation of new words from other forms. New words may be completely different categories. Friend friendly friendliness
  • 25. Words (Contd.,) • Traditionally words are classified into different categories based on their uses. • First – word’s contribution to the meaning of the phrase that contains it • Second – the actual syntactic structure in which the word play a role • Noun and Adjective • Noun – identify the basic type of object • Adjective – qualify the object, concept of place • The green book. Green books • That green is lighter than the other • Modifiers can be noun modifier and adjective modifier.
  • 26. • Four main classes of words • Nouns • Verbs • Adjectives • Adverbs • Other classes • Articles • Pronouns • Prepositions • Particles • Quantifiers • Conjunctions and so on. Words (Contd.,)
  • 27. • Head of the Phrase: A word in any of four open classes: • Noun Phrase: • The elephant • An elderly elephant • The angry elephant killed two men • Adjective Phrase • Thirsty • Very thirsty • Thirsty made him to do so Words (Contd.,)
  • 28. • Sometimes head requires additional phrases following it to express the desired meaning. • Example: ‘put’ cannot form a verb phrase in isolation. • John put - cannot be a sentence. • Instead, john put dog in the house. • Sentence can be completed using complement • The phrase or set of phrases needed to complete the meaning of head is called the complement. • In the above example, house is complement. Words (Contd.,)
  • 29. Noun Phrases Verb Phrases The president of the company Looked up the chimney His desire to succeed Believed that the world was flat Several challenges from the opposing team Ate the pizza Adjective Phrases Adverbial Phrases It is easy to assemble Rapidly like a bat I am happy that he won the prize Intermittently throughout the day He is angry as a hippo Inside the house Words (Contd.,)
  • 30. The elements of simple noun phrases • Noun phrases (NPs) are used to refer to things: objects, places, concepts, events, qualities and so on. • The simplest NP consists of a single pronoun. Pronouns can refer to physical objects, to objects, to qualities and sometimes takes any modifiers. • It hid under the rug • Once I opened the door, I regretted it for months • He was so angry, but he didn’t show it. • He who hesitates is lost. (pronouns taking modifiers very rarely)
  • 31. • Proper noun is also used. • Head of noun phrase is usually a common noun. • Nouns divide into two main classes: • Count nouns – describe specific objects or sets of objects • Mass nouns – describe composites or substances • Noun phrase may contain specifiers and qualifiers preceding the head. • Qualifiers describe the general class of objects identified by the head. • Specifiers describe how many such objects are described. The elements of simple noun phrases
  • 32. • Specifiers are constructed out of • Ordinals like first and second • Cardinals like one and two • Determiners • Determiners has following divisions • Articles – a, an and the. • Demonstratives – this, that, these and those. • Possessives – noun phrases followed by the suffix ‘s. Ajay’s . Possessive pronouns are her, my and whose. • Wh-determiners – words used in questions, which and what. • Quantifying determiners – some, every, most so, any, both and half. The elements of simple noun phrases
  • 33. • A simple noun phrase may have at most one determiner, one ordinal and one cardinal. • A sentence may have all three – first three contestants. • Sentence may contain few quantifying determiners – few songs we knew • The qualifiers in a noun phrase occur after the specifiers (if any) and before the head. They consist of adjectives and nouns being used as modifiers. • Adjectives – words that attribute qualities to objects yet do not refer to the qualities themselves. Angry is an adjective that attributes the quality of anger to something • Noun modifiers – mass or count nouns used to modify another noun. Cook book or the ceiling paint can. The elements of simple noun phrases
  • 34. • Pronouns take forms based on : • Person – first, second and third. • Gender – masculine, feminine and neutral. • In some languages nouns are classified by their gender (French) • Pronouns distinguish number, person, gender and case (possessive, subject or object) The elements of simple noun phrases
  • 35. Number First person Second person Third person Singular I You He, she it Plural We You they The elements of simple noun phrases Number First person Second person Third person Singular My Your His, her, its Plural our Your Their Pronouns as subject Pronouns possessiveness Number First person Second person Third person Singular Me You Him, her, it Plural us you them
  • 36. • A sentence is used to assert, query or command. • Mood – The way a sentence is used Verb Phrases and Simple sentences Mood Example Declarative or assertion The cat is sleeping Yes/no question Is the cat sleeping? Wh-question What is sleeping? Or which cat is sleeping? Imperative (or command) Shoot the cat!
  • 37. • Verbs can be divided into several different classes: • The auxiliary verbs – be, do and have • The modal verbs – will, can and could • The main verbs – eat, ran and believe Verb Phrases and Simple sentences