SlideShare a Scribd company logo
Compound Noun Polysemy and Sense
Enumeration in WordNet
1Abed Alhakim Freihat, 2Biswanath Dutta and
1Fausto Giunchiglia
1DISI, University of Trento
Trento, Italy
2Indian Statistical Institute (ISI)
Bangalore, India
eKNOW-2015, 22-27 February 2015, Lisbon, Portugal. 1
Outlines
 Problem
 WordNet
 Compound Nouns
 Polysemy
 Compound Noun Polysemy
 Sense Enumerations in Compound Nouns
 Solution
 Detecting Sense Enumerations in WordNet
 Results
 Conclusion and Future Work
2
WordNet (Princeton WordNet)
 A lexical Database for English
 A set of one or more synonyms (similar words) called a
synset
#1 pizza, pizza pie: Italian open pie made of thin bread dough spread with a
spiced mixture of e.g. tomato sauce and cheese.
 Organized through semantic and lexical relations
 Semantic Relations between synsets
 hypernym, hyponym, meronym, …
 Lexical Relations between words
 Antonym, derivationally related form, ...
3
Compound Nouns
 Multi-words or collocations that consist of noun modifier
and modified nouns.
 Nerve center
 Nerve is the noun modifier
 Center is the modified noun
 Red Coral
 Red is the noun modifier
 Coral is the modified noun
4
Polysemy
 A word is Polysemous if
 It has more than one meaning (i.e., It belongs to more than
one synset)
BANK
HONEY
5
Compound Noun Polysemy
 The cases where we use the modified noun to refer to
several different compound nouns.
 Using the word Center to refer:
 center, centre, nerve center, nerve centre -- a cluster of nerve cells governing
a specific bodily process.
 plaza, mall, center, shopping mall, shopping center, shopping centre --
mercantile establishment consisting of a carefully landscaped complex of
shops representing leading merchandisers; usually includes restaurants and
a convenient parking area; a modern version of the traditional marketplace.
 Using the word head to refer:
 fountainhead, drumhead, head teacher, …
6
Statistics
#Nouns 104290
#Synsets that contain these nouns 74314
#Compound nouns 58946
#Synsets that contain at least one
compound noun
40560
#Compound polysemous nouns 3407
7
• More than 56% of the nouns in WordNet are compound
nouns.
• More than 45% of the synsets contain compound nouns.
Types of Compound Noun Polysemy
• *Specialization polysemy:
• Using the word turtledove to refer:
#1 Australian turtledove, turtledove, Stictopelia cuneata: small
Australian dove
#2 turtledove: any of several Old World wild doves.
• Metonymy:
• Using the word cherry to refer:
• #2 cherry, cherry tree: any of numerous trees and shrubs
producing a small fleshy round fruit with a single hard stone.
• #3 cherry: a red fruit with a single hard stone.
• Sense enumerations
*Freihat, A. A., Giunchiglia, F. and Dutta, B. (2013). Solving specialization polysemy in WordNet. International Journal of
Computational Linguistics and Applications, vol. 4, no. 1, pp. 29-52. 8
Sense Enumeration in Compound Nouns
• Assignment of the noun modifier or the modified noun as a
synonym of the compound noun itself.
• Storing this kind of polysemy in a lexical database leads to a
redundant explosion of the word meanings.
• E.g., WordNet contains 135 non polysemous synsets in
which the term head is a noun modifier/modified noun of a
compound noun. Word head should have 168 senses (at
present 33 + 135 to add).
• WordNet assigns modified noun as a synonym of the
compound noun inconsistently.
9
Sense Enumeration in Compound Nouns
(contd.)
• Possible solutions
• Adding the modified noun as a synoym to all its
corresponding compound nouns → redundancy
• Removing this kind of polysemy → our proposed solution
10
Disambiguating Compound Nouns
 We use usually modified nouns to refer to their corresponding
compound nouns (e.g., center to refer: shopping center,
research center, medical center,...)
 Is it necessary to store the compound nouns and their
corresponding modified nouns as synonyms in the lexicon?
 Disambiguating the modified nouns …
 Are we able to disambiguate modified nouns because
 We store the synonymy in our mental lexicon, OR
 It is a syntactic process that does not depend on the
lexicon?
11
Discovery and Elimination of Sense
Enumerations in Compound Nouns
 Two phases:
 Discovery of sense enumerations in Compound
Nouns
 A semi automatic process
 Elimination of sense enumerations
 An automatic process
12
Discovery of sense enumerations in
Compound Nouns (phase I)
 Semi automatic:
 Deploying an algorithm that returns sense enumeration
candidates in compound noun the polysemous nouns.
 The algorithm excludes:
 Specialization polysemy instances
 Metonymy instances
 Exclusion of false positives.
 This step is manual where we exclude the false positives
 We exclude: missing adjunct noun/modified noun synset
and term abbreviations.
13
Discovery of sense enumerations in
Compound Nouns (phase I Contd…)
 Exclusion of false positives:
 Missing adjunct noun/ modified noun:
#1 party, political party -- an organization to gain political power.
#2. party -- an occasion on which people can assemble for social interaction and
entertainment.
#3. party, company -- a band of people associated temporarily in some activity.
#4. party -- a group of people gathered together for pleasure.
#5. party -- a person involved in legal proceedings.
 Term abbreviation
milliliter, millilitre, mil, ml, cubic centimeter, cubic centimetre, cc -- a metric unit of
volume equal to one thousandth of a liter.
14
Elimination of Sense Enumerations in
Compound Nouns (phase II)
 An automatic process:
 We eliminate the sense enumerations by removing the
polysemous modified nouns.
 E.g., applying the function on head, the synset #32 is
the synset #32':
#32 drumhead, head: a membrane that is stretched taut
over a drum.
#32' drumhead: a membrane that is stretched taut over a
drum.
15
Result and Evaluation
Results of the discovery of the algorithm.
Manual validation result.
Disambiguation algorithm result.
• In 80% cases, there is total agreement between the two evaluators.
• In 94% cases, there is partial agreement between the two evaluators.
16
#Compound noun polysemous terms 2270
#Compound noun polysemous synsets 2952
#Compound noun polysemous instances 11650
#Compound noun polysemous terms 1905
#Compound noun polysemous synsets 2547
#Compound noun polysemous instances 11088
#Nouns #Synsets #Senses
Before applying the algorithm 104290 74314 130207
After applying the algorithm 104290 74314 127660
Conclusion
• Sense enumeration in compound noun is a source of
noise rather than a source of knowledge.
• Which compound noun polysemus nouns we should store
in a lexical dayabase?
• Only metonymy
• Lexicon should avoid redundant information that can be
derived by syntactic rules or by NLP tools.
17
Future work
• Evaluation in terms of recall and precision to test our approach
• Examine the relation between sense enumeration and missing
terms.
• e.g., bony pelvis and head of muscle are missing in the
following two synsets respectively:
#25 head: the rounded end of a bone that bits into a
rounded cavity in another bone to form a joint.
#26 head: that part of a skeletal muscle that is away from
the bone that it moves.
18
Acknowledgement
• The research leading to these results has received funding from
the European Community’s Seventh Framework Program under
grant agreement n. 600854, Smart Society (http://www.smart-
society-project.eu/).
19
Thank you
Obrigado
Grazie
‫شكرا‬‫لكم‬
for kind attention!!!
bisu@drtc.isibang.ac.in
20

More Related Content

What's hot

referát.doc
referát.docreferát.doc
referát.doc
butest
 
Why parsing is a part of Language Faculty Science (by Daisuke Bekki)
Why parsing is a part of Language Faculty Science (by Daisuke Bekki)Why parsing is a part of Language Faculty Science (by Daisuke Bekki)
Why parsing is a part of Language Faculty Science (by Daisuke Bekki)
Daisuke BEKKI
 
NEW_PPT
NEW_PPTNEW_PPT
Latest trends in NLP - Exploring BERT
Latest trends in NLP -  Exploring BERTLatest trends in NLP -  Exploring BERT
Latest trends in NLP - Exploring BERT
Silversparro Technologies
 
Ai lecture 09(unit03)
Ai lecture  09(unit03)Ai lecture  09(unit03)
Ai lecture 09(unit03)
vikas dhakane
 
Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...
Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...
Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...
Grammarly
 
UWB semeval2016-task5
UWB semeval2016-task5UWB semeval2016-task5
UWB semeval2016-task5
Lukáš Svoboda
 
Towards Building Semantic Role Labeler for Indian Languages
Towards Building Semantic Role Labeler for Indian LanguagesTowards Building Semantic Role Labeler for Indian Languages
Towards Building Semantic Role Labeler for Indian Languages
Algoscale Technologies Inc.
 
Doppl development iteration #4
Doppl development   iteration #4Doppl development   iteration #4
Doppl development iteration #4
Diego Perini
 
Ai lecture 10(unit03)
Ai lecture  10(unit03)Ai lecture  10(unit03)
Ai lecture 10(unit03)
vikas dhakane
 

What's hot (10)

referát.doc
referát.docreferát.doc
referát.doc
 
Why parsing is a part of Language Faculty Science (by Daisuke Bekki)
Why parsing is a part of Language Faculty Science (by Daisuke Bekki)Why parsing is a part of Language Faculty Science (by Daisuke Bekki)
Why parsing is a part of Language Faculty Science (by Daisuke Bekki)
 
NEW_PPT
NEW_PPTNEW_PPT
NEW_PPT
 
Latest trends in NLP - Exploring BERT
Latest trends in NLP -  Exploring BERTLatest trends in NLP -  Exploring BERT
Latest trends in NLP - Exploring BERT
 
Ai lecture 09(unit03)
Ai lecture  09(unit03)Ai lecture  09(unit03)
Ai lecture 09(unit03)
 
Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...
Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...
Grammarly AI-NLP Club #6 - Sequence Tagging using Neural Networks - Artem Che...
 
UWB semeval2016-task5
UWB semeval2016-task5UWB semeval2016-task5
UWB semeval2016-task5
 
Towards Building Semantic Role Labeler for Indian Languages
Towards Building Semantic Role Labeler for Indian LanguagesTowards Building Semantic Role Labeler for Indian Languages
Towards Building Semantic Role Labeler for Indian Languages
 
Doppl development iteration #4
Doppl development   iteration #4Doppl development   iteration #4
Doppl development iteration #4
 
Ai lecture 10(unit03)
Ai lecture  10(unit03)Ai lecture  10(unit03)
Ai lecture 10(unit03)
 

Viewers also liked

Ad polysemy
Ad polysemyAd polysemy
Ad polysemy
Sanja B
 
Lexical relations
Lexical relationsLexical relations
Lexical relations
Hina Honey
 
Polysemi warohmah hasanah
Polysemi warohmah hasanahPolysemi warohmah hasanah
Polysemi warohmah hasanah
warohmahhasanah31
 
Homonym & polysemy
Homonym & polysemyHomonym & polysemy
Radial categories franklin delacruz
Radial categories franklin delacruzRadial categories franklin delacruz
Radial categories franklin delacruz
Franklin De la Cruz
 
Sense relations
Sense relationsSense relations
Sense relations
Gustina Savhira
 
Homonymy
HomonymyHomonymy
homophone, homonomy, polysemy
homophone, homonomy, polysemyhomophone, homonomy, polysemy
homophone, homonomy, polysemy
stefani llontop
 
Synonymy and its types
Synonymy and its typesSynonymy and its types
Synonymy and its types
Farhang Ahmed
 
Semantic relation among words
Semantic relation among wordsSemantic relation among words
Semantic relation among words
Agradjaya Agradjaya
 
Semantics
SemanticsSemantics
A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...
A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...
A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...
AIMS (Agricultural Information Management Standards)
 
Ppt upload
Ppt uploadPpt upload
Ppt upload
Buhsra
 
Lecture 6 homonyms
Lecture 6 homonymsLecture 6 homonyms
Lecture 6 homonyms
Viktoriya Pobedimova
 
Semantic roles week 5
Semantic roles week 5Semantic roles week 5
Semantic roles week 5
zouhirgabsi
 
Polysemous and Homonymous expressions
Polysemous and Homonymous expressionsPolysemous and Homonymous expressions
Polysemous and Homonymous expressions
Juan Miguel Palero
 
Semantics: Seven types of meaning
Semantics: Seven types of meaningSemantics: Seven types of meaning
Semantics: Seven types of meaning
Miftadia Laula
 
SEMANTICS
SEMANTICS SEMANTICS
SEMANTICS
Hameel Khan
 
Sense relations & Semantics
Sense relations & SemanticsSense relations & Semantics
Sense relations & Semantics
Afuza Shara
 
Audience new
Audience newAudience new
Audience new
sad12341
 

Viewers also liked (20)

Ad polysemy
Ad polysemyAd polysemy
Ad polysemy
 
Lexical relations
Lexical relationsLexical relations
Lexical relations
 
Polysemi warohmah hasanah
Polysemi warohmah hasanahPolysemi warohmah hasanah
Polysemi warohmah hasanah
 
Homonym & polysemy
Homonym & polysemyHomonym & polysemy
Homonym & polysemy
 
Radial categories franklin delacruz
Radial categories franklin delacruzRadial categories franklin delacruz
Radial categories franklin delacruz
 
Sense relations
Sense relationsSense relations
Sense relations
 
Homonymy
HomonymyHomonymy
Homonymy
 
homophone, homonomy, polysemy
homophone, homonomy, polysemyhomophone, homonomy, polysemy
homophone, homonomy, polysemy
 
Synonymy and its types
Synonymy and its typesSynonymy and its types
Synonymy and its types
 
Semantic relation among words
Semantic relation among wordsSemantic relation among words
Semantic relation among words
 
Semantics
SemanticsSemantics
Semantics
 
A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...
A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...
A Pattern-Based Approach to Hyponymy Relation Acquisition for the Agricultura...
 
Ppt upload
Ppt uploadPpt upload
Ppt upload
 
Lecture 6 homonyms
Lecture 6 homonymsLecture 6 homonyms
Lecture 6 homonyms
 
Semantic roles week 5
Semantic roles week 5Semantic roles week 5
Semantic roles week 5
 
Polysemous and Homonymous expressions
Polysemous and Homonymous expressionsPolysemous and Homonymous expressions
Polysemous and Homonymous expressions
 
Semantics: Seven types of meaning
Semantics: Seven types of meaningSemantics: Seven types of meaning
Semantics: Seven types of meaning
 
SEMANTICS
SEMANTICS SEMANTICS
SEMANTICS
 
Sense relations & Semantics
Sense relations & SemanticsSense relations & Semantics
Sense relations & Semantics
 
Audience new
Audience newAudience new
Audience new
 

Similar to Compound Noun Polysemy and Sense Enumeration in WordNet

NLP
NLPNLP
AtencíOn CapíTulo 3
AtencíOn CapíTulo 3AtencíOn CapíTulo 3
AtencíOn CapíTulo 3
Bernadette Delgado
 
AtencíOn CapíTulo 3
AtencíOn CapíTulo 3AtencíOn CapíTulo 3
AtencíOn CapíTulo 3
Bernadette Delgado
 
Atencion Capitulo 3
Atencion Capitulo 3Atencion Capitulo 3
Atencion Capitulo 3
Bernadette Delgado
 
Attention and Consciousness
Attention and ConsciousnessAttention and Consciousness
Attention and Consciousness
orengomoises
 
Atencion-Capitulo-3.ppt
Atencion-Capitulo-3.pptAtencion-Capitulo-3.ppt
Atencion-Capitulo-3.ppt
orengomoises
 
Analysis of lexico syntactic patterns for antonym pair extraction from a turk...
Analysis of lexico syntactic patterns for antonym pair extraction from a turk...Analysis of lexico syntactic patterns for antonym pair extraction from a turk...
Analysis of lexico syntactic patterns for antonym pair extraction from a turk...
csandit
 
ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...
ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...
ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...
cscpconf
 
Analysis of anaphora resolution system for
Analysis of anaphora resolution system forAnalysis of anaphora resolution system for
Analysis of anaphora resolution system for
ijitjournal
 
Word sense disambiguation using wsd specific wordnet of polysemy words
Word sense disambiguation using wsd specific wordnet of polysemy wordsWord sense disambiguation using wsd specific wordnet of polysemy words
Word sense disambiguation using wsd specific wordnet of polysemy words
ijnlc
 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
Pranav Gupta
 
Anaphora resolution in hindi language using gazetteer method
Anaphora resolution in hindi language using gazetteer methodAnaphora resolution in hindi language using gazetteer method
Anaphora resolution in hindi language using gazetteer method
ijcsa
 
Thinking and Language
Thinking and LanguageThinking and Language
Thinking and Language
lorilynw
 
The Evolution of Speech Segmentation: A Computer Simulation
The Evolution of Speech Segmentation: A Computer SimulationThe Evolution of Speech Segmentation: A Computer Simulation
The Evolution of Speech Segmentation: A Computer Simulation
Richard Littauer
 
Sentence level sentiment polarity calculation for customer reviews by conside...
Sentence level sentiment polarity calculation for customer reviews by conside...Sentence level sentiment polarity calculation for customer reviews by conside...
Sentence level sentiment polarity calculation for customer reviews by conside...
eSAT Publishing House
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
Toine Bogers
 
detect emotion from text
detect emotion from textdetect emotion from text
detect emotion from text
Safayet Hossain
 
Class14
Class14Class14
NLP
NLPNLP
NLP
NLPNLP

Similar to Compound Noun Polysemy and Sense Enumeration in WordNet (20)

NLP
NLPNLP
NLP
 
AtencíOn CapíTulo 3
AtencíOn CapíTulo 3AtencíOn CapíTulo 3
AtencíOn CapíTulo 3
 
AtencíOn CapíTulo 3
AtencíOn CapíTulo 3AtencíOn CapíTulo 3
AtencíOn CapíTulo 3
 
Atencion Capitulo 3
Atencion Capitulo 3Atencion Capitulo 3
Atencion Capitulo 3
 
Attention and Consciousness
Attention and ConsciousnessAttention and Consciousness
Attention and Consciousness
 
Atencion-Capitulo-3.ppt
Atencion-Capitulo-3.pptAtencion-Capitulo-3.ppt
Atencion-Capitulo-3.ppt
 
Analysis of lexico syntactic patterns for antonym pair extraction from a turk...
Analysis of lexico syntactic patterns for antonym pair extraction from a turk...Analysis of lexico syntactic patterns for antonym pair extraction from a turk...
Analysis of lexico syntactic patterns for antonym pair extraction from a turk...
 
ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...
ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...
ANALYSIS OF LEXICO-SYNTACTIC PATTERNS FOR ANTONYM PAIR EXTRACTION FROM A TURK...
 
Analysis of anaphora resolution system for
Analysis of anaphora resolution system forAnalysis of anaphora resolution system for
Analysis of anaphora resolution system for
 
Word sense disambiguation using wsd specific wordnet of polysemy words
Word sense disambiguation using wsd specific wordnet of polysemy wordsWord sense disambiguation using wsd specific wordnet of polysemy words
Word sense disambiguation using wsd specific wordnet of polysemy words
 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
 
Anaphora resolution in hindi language using gazetteer method
Anaphora resolution in hindi language using gazetteer methodAnaphora resolution in hindi language using gazetteer method
Anaphora resolution in hindi language using gazetteer method
 
Thinking and Language
Thinking and LanguageThinking and Language
Thinking and Language
 
The Evolution of Speech Segmentation: A Computer Simulation
The Evolution of Speech Segmentation: A Computer SimulationThe Evolution of Speech Segmentation: A Computer Simulation
The Evolution of Speech Segmentation: A Computer Simulation
 
Sentence level sentiment polarity calculation for customer reviews by conside...
Sentence level sentiment polarity calculation for customer reviews by conside...Sentence level sentiment polarity calculation for customer reviews by conside...
Sentence level sentiment polarity calculation for customer reviews by conside...
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 
detect emotion from text
detect emotion from textdetect emotion from text
detect emotion from text
 
Class14
Class14Class14
Class14
 
NLP
NLPNLP
NLP
 
NLP
NLPNLP
NLP
 

Recently uploaded

みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
名前 です男
 
How to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptxHow to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptx
danishmna97
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
panagenda
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
Neo4j
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
SOFTTECHHUB
 
How to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For FlutterHow to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For Flutter
Daiki Mogmet Ito
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Safe Software
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Mariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceXMariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceX
Mariano Tinti
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
Neo4j
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
innovationoecd
 
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Speck&Tech
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
Quotidiano Piemontese
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
Adtran
 
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
Edge AI and Vision Alliance
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
DianaGray10
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
Pixlogix Infotech
 

Recently uploaded (20)

みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
 
How to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptxHow to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptx
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
 
How to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For FlutterHow to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For Flutter
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Mariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceXMariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceX
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
 
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
 
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
 

Compound Noun Polysemy and Sense Enumeration in WordNet

  • 1. Compound Noun Polysemy and Sense Enumeration in WordNet 1Abed Alhakim Freihat, 2Biswanath Dutta and 1Fausto Giunchiglia 1DISI, University of Trento Trento, Italy 2Indian Statistical Institute (ISI) Bangalore, India eKNOW-2015, 22-27 February 2015, Lisbon, Portugal. 1
  • 2. Outlines  Problem  WordNet  Compound Nouns  Polysemy  Compound Noun Polysemy  Sense Enumerations in Compound Nouns  Solution  Detecting Sense Enumerations in WordNet  Results  Conclusion and Future Work 2
  • 3. WordNet (Princeton WordNet)  A lexical Database for English  A set of one or more synonyms (similar words) called a synset #1 pizza, pizza pie: Italian open pie made of thin bread dough spread with a spiced mixture of e.g. tomato sauce and cheese.  Organized through semantic and lexical relations  Semantic Relations between synsets  hypernym, hyponym, meronym, …  Lexical Relations between words  Antonym, derivationally related form, ... 3
  • 4. Compound Nouns  Multi-words or collocations that consist of noun modifier and modified nouns.  Nerve center  Nerve is the noun modifier  Center is the modified noun  Red Coral  Red is the noun modifier  Coral is the modified noun 4
  • 5. Polysemy  A word is Polysemous if  It has more than one meaning (i.e., It belongs to more than one synset) BANK HONEY 5
  • 6. Compound Noun Polysemy  The cases where we use the modified noun to refer to several different compound nouns.  Using the word Center to refer:  center, centre, nerve center, nerve centre -- a cluster of nerve cells governing a specific bodily process.  plaza, mall, center, shopping mall, shopping center, shopping centre -- mercantile establishment consisting of a carefully landscaped complex of shops representing leading merchandisers; usually includes restaurants and a convenient parking area; a modern version of the traditional marketplace.  Using the word head to refer:  fountainhead, drumhead, head teacher, … 6
  • 7. Statistics #Nouns 104290 #Synsets that contain these nouns 74314 #Compound nouns 58946 #Synsets that contain at least one compound noun 40560 #Compound polysemous nouns 3407 7 • More than 56% of the nouns in WordNet are compound nouns. • More than 45% of the synsets contain compound nouns.
  • 8. Types of Compound Noun Polysemy • *Specialization polysemy: • Using the word turtledove to refer: #1 Australian turtledove, turtledove, Stictopelia cuneata: small Australian dove #2 turtledove: any of several Old World wild doves. • Metonymy: • Using the word cherry to refer: • #2 cherry, cherry tree: any of numerous trees and shrubs producing a small fleshy round fruit with a single hard stone. • #3 cherry: a red fruit with a single hard stone. • Sense enumerations *Freihat, A. A., Giunchiglia, F. and Dutta, B. (2013). Solving specialization polysemy in WordNet. International Journal of Computational Linguistics and Applications, vol. 4, no. 1, pp. 29-52. 8
  • 9. Sense Enumeration in Compound Nouns • Assignment of the noun modifier or the modified noun as a synonym of the compound noun itself. • Storing this kind of polysemy in a lexical database leads to a redundant explosion of the word meanings. • E.g., WordNet contains 135 non polysemous synsets in which the term head is a noun modifier/modified noun of a compound noun. Word head should have 168 senses (at present 33 + 135 to add). • WordNet assigns modified noun as a synonym of the compound noun inconsistently. 9
  • 10. Sense Enumeration in Compound Nouns (contd.) • Possible solutions • Adding the modified noun as a synoym to all its corresponding compound nouns → redundancy • Removing this kind of polysemy → our proposed solution 10
  • 11. Disambiguating Compound Nouns  We use usually modified nouns to refer to their corresponding compound nouns (e.g., center to refer: shopping center, research center, medical center,...)  Is it necessary to store the compound nouns and their corresponding modified nouns as synonyms in the lexicon?  Disambiguating the modified nouns …  Are we able to disambiguate modified nouns because  We store the synonymy in our mental lexicon, OR  It is a syntactic process that does not depend on the lexicon? 11
  • 12. Discovery and Elimination of Sense Enumerations in Compound Nouns  Two phases:  Discovery of sense enumerations in Compound Nouns  A semi automatic process  Elimination of sense enumerations  An automatic process 12
  • 13. Discovery of sense enumerations in Compound Nouns (phase I)  Semi automatic:  Deploying an algorithm that returns sense enumeration candidates in compound noun the polysemous nouns.  The algorithm excludes:  Specialization polysemy instances  Metonymy instances  Exclusion of false positives.  This step is manual where we exclude the false positives  We exclude: missing adjunct noun/modified noun synset and term abbreviations. 13
  • 14. Discovery of sense enumerations in Compound Nouns (phase I Contd…)  Exclusion of false positives:  Missing adjunct noun/ modified noun: #1 party, political party -- an organization to gain political power. #2. party -- an occasion on which people can assemble for social interaction and entertainment. #3. party, company -- a band of people associated temporarily in some activity. #4. party -- a group of people gathered together for pleasure. #5. party -- a person involved in legal proceedings.  Term abbreviation milliliter, millilitre, mil, ml, cubic centimeter, cubic centimetre, cc -- a metric unit of volume equal to one thousandth of a liter. 14
  • 15. Elimination of Sense Enumerations in Compound Nouns (phase II)  An automatic process:  We eliminate the sense enumerations by removing the polysemous modified nouns.  E.g., applying the function on head, the synset #32 is the synset #32': #32 drumhead, head: a membrane that is stretched taut over a drum. #32' drumhead: a membrane that is stretched taut over a drum. 15
  • 16. Result and Evaluation Results of the discovery of the algorithm. Manual validation result. Disambiguation algorithm result. • In 80% cases, there is total agreement between the two evaluators. • In 94% cases, there is partial agreement between the two evaluators. 16 #Compound noun polysemous terms 2270 #Compound noun polysemous synsets 2952 #Compound noun polysemous instances 11650 #Compound noun polysemous terms 1905 #Compound noun polysemous synsets 2547 #Compound noun polysemous instances 11088 #Nouns #Synsets #Senses Before applying the algorithm 104290 74314 130207 After applying the algorithm 104290 74314 127660
  • 17. Conclusion • Sense enumeration in compound noun is a source of noise rather than a source of knowledge. • Which compound noun polysemus nouns we should store in a lexical dayabase? • Only metonymy • Lexicon should avoid redundant information that can be derived by syntactic rules or by NLP tools. 17
  • 18. Future work • Evaluation in terms of recall and precision to test our approach • Examine the relation between sense enumeration and missing terms. • e.g., bony pelvis and head of muscle are missing in the following two synsets respectively: #25 head: the rounded end of a bone that bits into a rounded cavity in another bone to form a joint. #26 head: that part of a skeletal muscle that is away from the bone that it moves. 18
  • 19. Acknowledgement • The research leading to these results has received funding from the European Community’s Seventh Framework Program under grant agreement n. 600854, Smart Society (http://www.smart- society-project.eu/). 19
  • 20. Thank you Obrigado Grazie ‫شكرا‬‫لكم‬ for kind attention!!! bisu@drtc.isibang.ac.in 20