Learning Multilingual Semantics from Big Data on the Web
Gerard de Melo
Assistant Professor, Tsinghua University
http://gerard.demelo.org
Learning Multilingual Semantics from Big Data on the Web
Gerard de Melo
Assistant Professor, Tsinghua University
Big Data on the Web
Big Data on the WebBig Data on the Web Big Data on the Web
From Big Data to
From Big Data to
Multilingual Semantics?
Multilingual Semantics?
From Big Data to
From Big Data to
Multilingual Semantics?
Multilingual Semantics?
Image:
Manual Knowledge Organization Manual Knowledge Organization
Image: http://commons.wikimedia.org/wiki/File:Mundaneum_Tir%C3%A4ng_Karteikaarten.jpg Universal Bibliographic Repertory
(Repertoire Bibliographique Universel, RBU) by Paul Otlet and Henri La Fontaine in 1895
index cards with answers to queries
Universal Bibliographic Repertory
(Repertoire Bibliographique Universel, RBU) by Paul Otlet and Henri La Fontaine in 1895
Manual Knowledge Organization Manual Knowledge Organization
Image: Mundaneum
Universal Bibliographic Repertory
(Repertoire Bibliographique Universel, RBU) by Paul Otlet and Henri La Fontaine in 1895
index cards with answers to queries
Universal Bibliographic Repertory
(Repertoire Bibliographique Universel, RBU) by Paul Otlet and Henri La Fontaine in 1895
index cards with answers to queries
Alex Wright: This was a sort of “analog search engine”
Alex Wright: This was a sort of “analog search engine”
Zipfian Distribution
Zipfian DistributionZipfian Distribution Zipfian Distribution
Big Data on the Web
Big Data on the WebBig Data on the Web Big Data on the Web
Goal: Large Yet
Goal: Large Yet
Reasonably Clean Knowledge
Reasonably Clean Knowledge
Goal: Large Yet
Goal: Large Yet
Reasonably Clean Knowledge
Reasonably Clean Knowledge
Outline Outline
Large-Scale Knowledge Graphs
Semantics in Action Models for the Future
Outline Outline
Large-Scale Knowledge Graphs
Semantics in Action Models for the Future
Lexical Knowledge
Portuguese-Chinese Dictionary by Ruggieri et al. (1580s) The first European-Chinese dictionary
Provides translations, antonyms, etc.
Wiktionary Wiktionary
Wiktionary Wiktionary
Wiktionary Wiktionary
e.g. “salary” < Lat. “salarius” < Lat. “sal” (salt)
Etymological Wordnet Etymological Wordnet
LREC 2014
LREC 2014
Etymological Wordnet Etymological Wordnet
LREC 2014
LREC 2014
Etymological Wordnet Etymological Wordnet
Etymological Wordnet Etymological Wordnet Old English Example Old English Example
Lexical Ambiguities Lexical Ambiguities
Hipsters in London Images: https://www.flickr.com/photos/poisonbabyfood/4274634681 https://www.facebook.com/alexander.balabanov.82 Lexical Ambiguities Lexical Ambiguities
Reunion
Lexical Ambiguities Lexical Ambiguities
Reunion
Images:
https://commons.wikimedia.org/wiki/File:Reunions_Class_of_82_2007.jpg
https://commons.wikimedia.org/wiki/File:Riviere_Langevin_Trou_Noir_P1440224-35.jpg and many more...
and many more...
Lexical Ambiguities Lexical Ambiguities
Multilingual Lexical Knowledge
UWN: Universal Wordnet
Before:
manual work over two decades but not many large wordnets
Before:
manual work over two decades but not many large wordnets
Our Approach:
● Exploit translation
resources on the Web
● Learn regression model
with sophisticated graph-based features
Our Approach:
● Exploit translation
resources on the Web
● Learn regression model
with sophisticated graph-based features
UWN: Universal Wordnet
UWN: Universal Wordnet
over 1,000,000 words in over 100 languages
CIKM 2009
CIKM 2009 ICGL 2008ICGL 2008
Best Paper Award
Best Paper Award
ICGL 2008
ICGL 2008
Best Paper Award
Best Paper Award
UWN: Getting Started UWN: Getting Started
Simple API for JVM Languages
val uwn = new UWN(new File("plugins/"))
for (m <- uwn.getMeanings("souris", "fra")) println(m)
Or Just Download the TSV File
Simple API for JVM Languages
val uwn = new UWN(new File("plugins/"))
for (m <- uwn.getMeanings("souris", "fra")) println(m)
Adding Other Sources Gerard de Melo Language-specific, Language-specific, Domain-specific, Domain-specific, Arbitrary Databases Arbitrary Databases Language-specific, Language-specific, Domain-specific, Domain-specific, Arbitrary Databases Arbitrary Databases
Adding Other Sources
Adding Other SourcesAdding Other Sources Adding Other Sources
Adding Other Sources
Adding Other SourcesAdding Other Sources Adding Other Sources
Rob Matthews: printed small sample of Wikipedia
Actually, a printed Wikipedia corresponds to 2000 Britannica volumes Source: http://www.labnol.org/internet/wikipedia-printed-book/9136/ Actually, a printed Wikipedia corresponds to 2000 Britannica volumes Source: http://www.labnol.org/internet/wikipedia-printed-book/9136/
ACL 2010 AAAI 2013 ACL 2010 AAAI 2013 Use Identity Links to connect What is equivalent
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
ACL 2010 AAAI 2013
ACL 2010 AAAI 2013
Merging Structured Data Merging Structured Data
Trentino
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
One bad link is
One bad link is
enough to make a enough to make a connected component connected component inconsistent inconsistent
One bad link is
One bad link is
enough to make a enough to make a connected component connected component inconsistent inconsistent ACL 2010 AAAI 2013 ACL 2010 AAAI 2013
Source: Peter Mika
Entity Integration: Challenges
Entity Integration: Challenges
Merging Structured Data Merging Structured Data
Distinctness Assertions
Di =
({en: Province of Trento, en:Trentino},
{en:Trentino-South Tyrol,
en:Trentino-Alto Adige/Südtirol})
Distinctness Assertions
Di =
({en: Province of Trento, en:Trentino}, {en:Trentino-South Tyrol, en:Trentino-Alto Adige/Südtirol}) ACL 2010 AAAI 2013 ACL 2010 AAAI 2013
How to reconcile How to reconcile equivalence equivalence and and distinctness distinctness evidence? evidence? How to reconcile How to reconcile equivalence equivalence and and distinctness distinctness evidence? evidence? a) ignore some a) ignore some equivalence information equivalence information
(delete certain edges)
(delete certain edges)
a) ignore some
a) ignore some
equivalence information
equivalence information
(delete certain edges)
(delete certain edges) b) ignore some
b) ignore some
distinctness information
distinctness information
(remove node from
(remove node from
distinctness assertion) distinctness assertion) b) ignore some b) ignore some distinctness information distinctness information
(remove node from
(remove node from
distinctness assertion)
distinctness assertion)
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
ACL 2010 AAAI 2013
ACL 2010 AAAI 2013
Min. cost solution:
Min. cost solution:
NP-hard
NP-hard
APX-hard
APX-hard
Min. cost solution:
Min. cost solution:
NP-hard
NP-hard
APX-hard
APX-hard
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
ACL 2010 AAAI 2013
ACL 2010 AAAI 2013
Finally, use region growing
Finally, use region growing
algorithm in the spirit
algorithm in the spirit
of Leighton & Rao 1988
of Leighton & Rao 1988
Finally, use region growing
Finally, use region growing
algorithm in the spirit
algorithm in the spirit
of Leighton & Rao 1988
of Leighton & Rao 1988 Linear Program Relaxation
Linear Program Relaxation
Linear Program Relaxation
Linear Program Relaxation
Approximation Guarantee:
Approximation Guarantee:
4ln(nq+1)
4ln(nq+1)
for n distinctness assertions,
for n distinctness assertions,
q=max |D
q=max |Di,ji,j||
but independent of |D but independent of |Dii| !| ! Approximation Guarantee: Approximation Guarantee: 4ln(nq+1) 4ln(nq+1)
for n distinctness assertions,
for n distinctness assertions,
q=max |D q=max |D i,j i,j|| but independent of |D but independent of |Dii| !| !
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
Linear Program Relaxation
Linear Program Relaxation
Linear Program Relaxation
Linear Program Relaxation
Nice:
Nice:
This generalizes the
This generalizes the
Hungarian Algorithm Hungarian Algorithm to various advanced to various advanced types of non-standard types of non-standard matchings matchings (cf. de Melo. AAAI 2013) (cf. de Melo. AAAI 2013) Nice: Nice:
This generalizes the
This generalizes the
Hungarian Algorithm Hungarian Algorithm to various advanced to various advanced types of non-standard types of non-standard matchings matchings (cf. de Melo. AAAI 2013) (cf. de Melo. AAAI 2013)
Merging Structured Data
Merging Structured DataMerging Structured Data Merging Structured Data
Separated Concepts Separated Concepts (Multilingual Wikipedia) (Multilingual Wikipedia) Separated Concepts Separated Concepts (Multilingual Wikipedia) (Multilingual Wikipedia)
Application: Lexvo.org Semantic Web Semantic Web Journal 2014 Journal 2014 Semantic Web Semantic Web Journal 2014 Journal 2014
Lexvo.org Lexvo.org Semantic Web Semantic Web Journal 2014 Journal 2014 Semantic Web Semantic Web Journal 2014 Journal 2014
Semantic Web Semantic Web Journal 2014 Journal 2014 Semantic Web Semantic Web Journal 2014 Journal 2014 Interdisciplinary Interdisciplinary Work, e.g. in Work, e.g. in Digital Humanities Digital Humanities Interdisciplinary Interdisciplinary Work, e.g. in Work, e.g. in Digital Humanities Digital Humanities Lexvo.org Lexvo.org
Taxonomic Organization
a user wants a list of
„Art Schools in Europe“
Multilingual Taxonomies a Swedish user wants a list of „Konstskolor i Europa“
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach Taxonomic Integration: Taxonomic Integration: MENTA Approach MENTA Approach
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
De Melo & Weikum (2010).
CIKM Best Interdisciplinary Paper Award
Predict Individual Taxonomic Links: Article → Category Category → WordNet Predict Individual Taxonomic Links: Article → Category Category → WordNet Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Predict Individual Taxonomic Links: Article → Category Category → WordNet Predict Individual Taxonomic Links: Article → Category Category → WordNet Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA Image: https://de.wikipedia.org/wiki/Datei:Bersntol_palae.jpg Fersental
(Bersntol, Valle dei Mòcheni)
Fersental
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA https://de.wikipedia.org/wiki/Datei:Language_distribution_Trentino_2011.png Fersental
(Bersntol, Valle dei Mòcheni)
Fersental
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Use Identity Constraint Algorithm to form
equivalence classes
Use Identity Constraint Algorithm to form
equivalence classes
Markov Chain Random Walk with Restarts
to Rank Parents
Markov Chain Random Walk with Restarts
to Rank Parents Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Taxonomic Integration: Taxonomic Integration: MENTA MENTA Taxonomic Integration: Taxonomic Integration: MENTA MENTA
Bansal et al.
Bansal et al.
ACL 2014. Best Paper Runner-Up
ACL 2014. Best Paper Runner-Up
Bansal et al.
Bansal et al.
ACL 2014. Best Paper Runner-Up
ACL 2014. Best Paper Runner-UpBansal et al.ACL 2014. Best Paper Runner-UpBansal et al.ACL 2014. Best Paper Runner-UpBansal et al.ACL 2014. Best Paper Runner-UpBansal et al.ACL 2014. Best Paper Runner-Up Belief Propagation
Belief Propagation
exploiting Kirchhoff’s
exploiting Kirchhoff’s
Matrix Tree Theorem
Matrix Tree Theorem
for efficient handling of
for efficient handling of
tree factor tree factor Belief Propagation Belief Propagation exploiting Kirchhoff’s exploiting Kirchhoff’s
Matrix Tree Theorem
Matrix Tree Theorem
for efficient handling of
for efficient handling of
tree factor
tree factor
Chu-Liu-Edmonds
Chu-Liu-Edmonds
directed spanning tree
directed spanning tree
algorithm for decoding
algorithm for decoding
Chu-Liu-Edmonds
Chu-Liu-Edmonds
directed spanning tree
directed spanning tree
algorithm for decoding
algorithm for decoding New Algorithm:
Structured Output Prediction New Algorithm:
UWN/MENTA
CIKM 2010
CIKM 2010
Best Paper Award
Best Paper Award
CIKM 2010
CIKM 2010
Best Paper Award
Best Paper Award Biggest (ontological) Biggest (ontological) taxonomy taxonomy Biggest (ontological) Biggest (ontological) taxonomy taxonomy
UWN/MENTA
multilingual extension of WordNet for
word senses and taxonomical information over 200 languages
Outline Outline
Large-Scale Knowledge Graphs
Semantics in Action
Language Education
Language EducationLanguage Education Language Education
UWN UWNUWN UWN http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/
UWN UWNUWN UWN http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/
UWN UWNUWN UWN http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/
UWN UWNUWN UWN http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/ http://www.lexvo.org/uwn/
Application: Sense-Disambiguated Application: Sense-Disambiguated Example Sentences Example Sentences Application: Sense-Disambiguated Application: Sense-Disambiguated Example Sentences Example Sentences
Application: Sense-Disambiguated Application: Sense-Disambiguated Example Sentences Example Sentences Application: Sense-Disambiguated Application: Sense-Disambiguated Example Sentences Example Sentences
Application: Sense-Disambiguated Application: Sense-Disambiguated Example Sentences Example Sentences Application: Sense-Disambiguated Application: Sense-Disambiguated Example Sentences Example Sentences
Application:
Monolingual Language Users Application:
Application:
Monolingual Language Users Application:
Thesauri Thesauri
Thesauri Thesauri
Application: Machine Translation Application: Machine Translation
OpenWN-PT:
Used by Google Translate
OpenWN-PT:
Machine Learning Machine Learning
Examples
Incorrect Correct
Machine Learning Machine Learning Examples Learning Learning Incorrect
Machine Learning Machine Learning Examples Learning Learning Incorrect
Correct ClassifierModel
Machine Learning Machine Learning
Examples ProbablyIncorrect!
Learning
Learning PredictionPrediction
Incorrect
Better Machine Learning Better Machine Learning
Examples ProbablyIncorrect!
Learning
Learning PredictionPrediction
Incorrect
Correct ClassifierModel
Better Classifier!
+
Better Labels for Test DataUWN Senses in MT? Issue: Senses should be less fine-grained Issue: Senses should be less fine-grained
No Word Left Behind
No Word Left Behind
No Word Left Behind
No Word Left Behind
Similar: Part-Of-Speech Tagging Similar: Part-Of-Speech Tagging
● British fans gathered at the stadium to... ADJECTIVE “Didgeridoo” is similar to: “horn” (NOUN) “drums” (NOUN) “accordion” (NOUN) “Didgeridoo” is similar to: “horn” (NOUN) “drums” (NOUN) “accordion” (NOUN)
Didgeridoo fans gathered at the park to...
Similar: Part-Of-Speech Tagging Similar: Part-Of-Speech Tagging
● British fans gathered at the stadium to... ADJECTIVE Gaelic “didiridiú” translates to “didgeridoo” (NOUN) in English Gaelic “didiridiú” translates to “didgeridoo” (NOUN) in English ...Astrálach is ea an didiridiú ???
Sentence Level Sentence Level
Sentence Level Sentence Level
Sentence Level Sentence Level
What about
Document-Level Tasks? What about
Document-Level Tasks?
“new” 1.0 “york” 1.0 “jaguar” 1.0 “automobile” 0.0 “car” 0.0 “10th” 1.0 “street” 1.0 “show” 1.0 ... ... New_York 1.0 Jaguar (car) 0.0 Jaguar (animal) 1.0 Automobile/Car 0.0 10th Street 1.0 Performance 1.0 ... ...
“10th street new york jaguar show” Similar:
“10th New show in York” “New Jaguar show”
“Show New Street in York”
“10th street new york jaguar show” Similar:
“10th street nyc jaguar show”
Document Level Document Level
“new” 1.0 “york” 1.0 “jaguar” 1.0 “automobile” 0.0 “car” 0.0 “10th” 1.0 “street” 1.0 “show” 1.0 ... ... New_York 1.0 Jaguar (car) 0.0 Jaguar (animal) 1.0 Automobile/Car 0.0 10th Street 1.0 Performance 1.0 ... ... Animal 0.5 Vehicle 0.0
“10th street new york jaguar show” Similar:
“10th New show in York” “New Jaguar show”
“Show New Street in York”
“10th street new york jaguar show” Similar:
“10th street nyc jaguar show” “10th street nyc animal show”
“Exposición de jaguares Nueva York”
Expansion (de Melo &
Siersdorfer 2007)
Document Level Document Level
Given: training documents with class labels
Goal: guess class labels for test documents in some other language
Result: better than plain machine translation. See de Melo & Siersdorfer 2007.
Multilingual Tasks:
Cross-Lingual Text Classification Multilingual Tasks:
Underlying frame: Commercial transfer
Capture the “who-did-what-to-whom” Microsoft bought the patent from Nokia. Nokia sold the patent to Microsoft.
The patent was acquired by Microsoft [from Nokia]. The patent was sold [by Nokia] to Microsoft.
Sentence-Level Semantics Sentence-Level Semantics
Buyer: Microsoft Seller: Nokia
FrameBase.org
Bringing knowledge into a standard form based on natural language (FrameNet)
Bringing knowledge into a standard form based on natural language (FrameNet)
ESWC 2015 Best Student Paper Nominee ESWC 2015 Best Student Paper Nominee
Relation Integration Relation Integration X isAuthorOf Y Y writtenBy X X wrote Y Y writtenInYear Z ESWC 2015 Best Student Paper Nominee ESWC 2015 Best Student Paper Nominee
Relation Integration Relation Integration
YAGO: isMarriedTo predicate
YAGO: isMarriedTo predicate
Freebase: Marriage Entity
Freebase: Marriage Entity
Challenge: Modelling Differences Challenge: Modelling Differences
Search Interfaces
“Which companies were created during the last century in Silicon Valley ?”
YAGO2:
WWW 2011 Best Demo Award
YAGO2:
WWW 2011 Best Demo Award
Answering Questions
IBM's Jeopardy!-winning Watson system
Answering Questions
IBM's Jeopardy!-winning Watson system
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
The Roman Empire was remarkably
multicultural, with ”a rather astonishing cohesive capacity” to create a sense of shared identity while encompassing diverse peoples within its political
system over a long span of time.
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
The Roman Empire was remarkably
multicultural, with ”a rather astonishing cohesive capacity” to create a sense of shared identity while encompassing diverse peoples within its political
system over a long span of time. syntactic
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
The Roman Empire was remarkably
multicultural, with ”a rather astonishing cohesive capacity” to create a sense of shared identity while encompassing diverse peoples within its political
system over a long span of time. syntactic semantic!
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
The Roman Empire was remarkably
multicultural, with ”a rather astonishing cohesive capacity” to create a sense of shared identity while encompassing diverse peoples within its political
system over a long span of time. semantic!
syntactic syntactic?
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
The Roman Empire was remarkably
multicultural, with ”a rather astonishing cohesive capacity” to create a sense of shared identity while encompassing diverse peoples within its political
system over a long span of time. semantic!
syntactic syntactic? ?
What Goes into Word Vectors?
What Goes into Word Vectors?What Goes into Word Vectors? What Goes into Word Vectors?
The Roman Empire was remarkably
multicultural, with ”a rather astonishing cohesive capacity” to create a sense of shared identity while encompassing diverse peoples within its political
system over a long span of time. semantic! syntactic ? Word2Vec Solution: Subsampling Word2Vec Solution: Subsampling syntactic?
Word2Vec Approach
Word2Vec ApproachWord2Vec Approach Word2Vec Approach Alexandre Duret-Lutz https://www.flickr.com/photos/gadl/110845690/ Take everything we can get Take everything we can get
Our Proposal:
Our Proposal:
Extract the Most Valuable Parts
Extract the Most Valuable Parts
Our Proposal:
Our Proposal:
Extract the Most Valuable Parts
Extract the Most Valuable Parts
…Greek and Roman mythology...
Our Proposal:
Our Proposal:
Extract the Most Valuable Parts
Extract the Most Valuable Parts
Our Proposal:
Our Proposal:
Extract the Most Valuable Parts
Extract the Most Valuable Parts
semantic!
look for semantically salient contexts in text!
look for semantically salient contexts in text!
Two Worlds Two Worlds
Jiaqiang Chen and Gerard de Melo 2015
Distributional Semantics:
Proposed Research Program: Joint Training
Proposed Research Program: Joint Training
Better
Word Embeddings Joint Training
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Proposed Research Program: Joint Training
Proposed Research Program: Joint Training
Better
Word Embeddings Joint Training
Jiaqiang Chen and Gerard de Melo 2015
Use parallel threads
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Joint Training Joint Training Preliminary Experiments: Preliminary Experiments: Joint Training Joint Training
Recently lots of related work: E.g. Faruqui et al., Hill & Korhonen,
Wang et al., Johansson & Nieto Piña
Recently lots of related work: E.g. Faruqui et al., Hill & Korhonen,
Wang et al., Johansson & Nieto Piña
Preliminary Experiments: Preliminary Experiments: Joint Training Joint Training Preliminary Experiments: Preliminary Experiments: Joint Training Joint Training
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Joint Training Joint Training Preliminary Experiments: Preliminary Experiments: Joint Training Joint Training
Use negative sampling
Use negative sampling
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction
Jiaqiang Chen and Gerard de Melo 2015
Variant 1: Definition Extraction
Variant 1: Definition Extraction
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction
Jiaqiang Chen and Gerard de Melo 2015 Definitions
befuddle: to becloud and confuse as with liquor befuddled: dazed by alcoholic drink
befuddled: confused and vague used especially of thinking beg: to ask earnestly for, to entreat or supplicate for, to beseech
Variant 1: Definition Extraction
Variant 1: Definition Extraction
Source: GCIDE
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Synonyms
effectual: effectual efficacious effective
effectuality: effectiveness effectivity effectualness efficacious: effectual
efficaciousness: efficacy
Jiaqiang Chen and Gerard de Melo 2015
Variant 1: Definition Extraction
Variant 1: Definition Extraction
Source: GCIDE
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction
Jiaqiang Chen and Gerard de Melo 2015
Variant 2: List Extraction
Variant 2: List Extraction
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction
Jiaqiang Chen and Gerard de Melo 2015
● Look for repeated occurrences of commas ● Short units of roughly equal length
● noun phrases, adjectives
Variant 2: List Extraction
Variant 2: List Extraction
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction
Jiaqiang Chen and Gerard de Melo 2015
● Look for repeated occurrences of commas ● Short units of roughly equal length
● noun phrases, adjectives ● Also: Hearst patterns, e.g.
“cities such as New York, London, ...”
Variant 2: List Extraction
Variant 2: List Extraction
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction Preliminary Experiments: Preliminary Experiments: Information Extraction Information Extraction
Jiaqiang Chen and Gerard de Melo 2015 Extracted Lists
player captain manager director vice-chairman
group race culture religion organisation person person Italian Mexican Chinese Creole French
Self-Portraits Portraits iris Still-Lives with Sunflowers view from the Asylum Works after Millet Vineyards
ballscrews leadscrews worm gear screwjacks linear actuator
Cleveland Essex Lincolnshire Northamptonshire Nottinghamshire Thames Valley South Wales
ant.py dimdriver.py dimdriverdatafile.py
dimdriverdatasetdef.py dimexception.py dimmaker.py dimoperators.py dimparser.py dimrex.py dimension.py
Variant 2: List Extraction
Preliminary Experiments: Preliminary Experiments: Setup Setup Preliminary Experiments: Preliminary Experiments: Setup Setup Wikipedia 2010
normalize to lower case and remove special characters Contain 1,205,009,010 words
Select words appearing at least 50 times Vocabulary size 220,521
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Setup Setup Preliminary Experiments: Preliminary Experiments: Setup Setup Wikipedia 2010
normalize to lower case and remove special characters Contain 1,205,009,010 words
Select words appearing at least 50 times Vocabulary size 220,521
Balance Components
simply by controlling starting learning rates: 0.05 for CBOW, varying rates for extracted information
Balance Components
simply by controlling starting learning rates: 0.05 for CBOW, varying rates for extracted information
Vector dim. 300
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Results on WS353 Results on WS353 Preliminary Experiments: Preliminary Experiments: Results on WS353 Results on WS353
Positive effect from 0.001 until around 0.04
Positive effect from 0.001 until around 0.04
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Example Example Preliminary Experiments: Preliminary Experiments: Example Example
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Preliminary Experiments: Preliminary Experiments: Example Example Preliminary Experiments: Preliminary Experiments: Example Example
Jiaqiang Chen and Gerard de Melo 2015
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Best Paper Award at NAACL 2015
Vector Space Modeling Workshop
Outline Outline
Large-Scale Knowledge Graphs
Semantics in Action
History Repeating?
History Repeating?History Repeating? History Repeating? SMT SMT NMTNMT Phrase-Based SMT Hierarchical Phrases WSD, MEANT etc. Phrase-Based SMT Hierarchical Phrases
Well-Known Issues
Well-Known IssuesWell-Known Issues Well-Known Issues
Source: The New Yorker Future: Future: Learning Common-Sense Learning Common-Sense Future: Future: Learning Common-Sense Learning Common-Sense
Learning Common-Sense
Learning Common-SenseLearning Common-Sense Learning Common-Sense WebChild AAAI 2014 WSDM 2014 AAAI 2011 WebChild AAAI 2014 WSDM 2014 AAAI 2011
Lexical Intensity Orderings Lexical Intensity Orderings
hot hot warm warm fiery fiery scorching scorching < < < weak strong TACL 2013 TACL 2013
Knowlywood: Human Activities Knowlywood: Human Activities
CIKM 2015
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships x x x x petronia sparrow parched arid x dry x bird http://www.wikihow.com/Read-a-Book-to-a-Baby-or-Infant#/Image:Read-a-Book-to-a-Baby-or-Infant-Step-5.jpg
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships x x x x petronia sparrow parched arid x dry x bird http://www.wikihow.com/Read-a-Book-to-a-Baby-or-Infant#/Image:Read-a-Book-to-a-Baby-or-Infant-Step-5.jpg
Should account for relationships (incl. affordances,
causality, etc.)
Should account for relationships (incl. affordances,
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships
Assume that she is learning just from text
Assume that she is learning just from text
1. Gather large amounts of Patterns
2. Use Web-Scale Data (Google N-Grams, derived from 10^12 words of text)
Hearst-style Bootstrapping with
large
numbers of seeds
Gerard de Melo
Information Extraction from Text Information Extraction from Text
Extension to Relationships Extension to Relationships
Commonsense word relationships extracted from Google 1T n-grams
24 relations bootstrapped via ConceptNet → 1,158,141 triples
Extension to Relationships Extension to Relationships
earring hasProperty gorgeous concept definedAs theory
sonar partOf submarine predator desires food
Commonsense word relationships extracted from Google 1T n-grams
24 relations bootstrapped via ConceptNet → 1,158,141 triples
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships
Extension to Relationships
Extension to RelationshipsExtension to Relationships Extension to Relationships
Summary
Large-Scale Knowledge Graphs ► Universal WordNet/MENTA:
large multilingual taxonomy ► Etymological WordNet
Semantics in Action, e.g. ► Lexvo.org
► Question Answering
with YAGO Future Perspectives
► Vector Representations ► Common-Sense for NLU
More Information: www.demelo.org gdm@demelo.org More Information: www.demelo.org gdm@demelo.org Gerard de Melo