SlideShare a Scribd company logo
1 of 18
Download to read offline
Latent Relational Model for Relation Extraction
Gaetano Rossiello1
, Alfio Gliozzo2
, Nicolas Fauceglia2
, Giovanni Semeraro1
1
Department of Computer Science - University of Bari, Italy
2
IBM Research AI - Yorktown Heights, NY, USA
gaetano.rossiello@uniba.it
github.com/gaetangate
/in/gaetano-rossiello
@tanoross
Goal: from Text to Knowledge
Unstructured Textual Data Structured Data Knowledge & Insights
● Information Extraction
○ Entity Recognition
○ Relation Extraction
● Frame Parsing
● Semantic Parsing
○ FOL
○ Lambda Calculus
○ AMR
● Deductive Reasoning
● Inductive Logic Programming
● Probabilistic (Logic) Programming
● Relational Embeddings
● ...
Why Relation Extraction?
● Automatic Knowledge Base Population (AKBP)
○ Lexical resources: add words to WordNet thesaurus
○ Fact bases: add facts to Wikidata or DBpedia
● Automatic Knowledge Base Construction (AKBC)
● Sample application: Question Answering (QA)
○ Who are the actors younger than Tom Hanks?
(isA ?x actor) (birthDate ?x ?y) (birthDate “Tom_Hanks” ?z) (> ?y ?z)
Relation Extraction Approaches
● Pattern-based [Hearst, 1992]
○ Hand-crafted rules
● Bootstrapping [Agichtein, 2000]
○ Semantic drift
● OpenIE [Banko, 2007; Fader, 2011; Mausam, 2012]
○ Lexicalized relations not in a canonical form
● Supervised [Jiang, 2007; Sun, 2014; Nguyen, 2015]
○ Manually annotated training examples
● Distant Supervision [Mintz, 2009; Lin, 2016; Glass, 2018]
○ An existing KB is used to generate training examples
○ Advantages from both bootstrapping and supervised RE
ISWC Semantic Web Challenge 2017
Glass, M., Gliozzo, A., Hassanzadeh, O., Mihindukulasooriya, N., Rossiello, G.
Inducing implicit relations from text using distantly supervised deep nets. ISWC 2018.
PCNN-KI: Piecewise Convolutional Neural Network for Distantly Supervised RE
PermID KG
Distantly Supervised RE: Limitations
● Distant Supervision does not fit well for vertical domains or long-tailed
relation types, where only a few seed examples are available
● The generalization capability is limited only to those relation types seen
during the training phase
Distantly supervised RE cannot be applied in other domains with new relation types
Use Case: Knowledge Base Population in Cold Start
Research Question:
How to design a method able to identify new
relation types in a (small) collection of
documents using a few examples?
Training examples
Relation Extraction as Analogy Problem
● Given a corpus D and an entity pair (a, b)
● Find the set R = {(x, y) ∊ D | a : b = x : y}
Watson : IBM = Pixel : Google
Query pair Result pair
Word Analogy using Distributional Semantic Models
Vector offset with Word Embeddings
man : king = woman : ?
vec(king) - vec(man) + vec (woman) ≈ vec(queen)
vec(king) - vec(man) ≈ vec(queen) - vec(woman)
Mikolov, T., Chen, K., Corrado, G., & Dean, J. Efficient estimation of word representations in vector space. ICLR 2013.
Pennington, J., Socher, R., & Manning, C. D. Glove: Global vectors for word representation. EMNLP 2014.
Levy, O., Goldberg, Y., & Dagan, I. Improving distributional similarity with lessons learned from word embeddings. TACL 2015.
Limitations:
● Handling multi-word (e.g. Tom Hanks) with pre-trained word embedding models
● Handling unseen words/entities
● Not effective on SAT Analogy Questions [Church, 2017]
SAT Analogy Questions Dataset
● SAT = Scholastic Aptitude Test [Turney, 2003]
● 374 multiple-choice analogy questions; 5 choices per question
● Human performance: 81.5%
● SOTA - Latent Relational Analysis (LRA): 56.1%
Turney, P.D., and Littman, M.L. Corpus-based learning of analogies and semantic relations. Machine Learning. 2005.
Turney, P.D. Similarity of semantic relations. Computational Linguistics. 2006.
LRA
r1 = vec(mason:stone)
r2 = vec(carpenter:wood)
sim = cosine(r1, r2)
Latent Relational Model for RE
Entity-Entity Vocabulary
V = {(X1, Y1),..., (Xn, Yn)}
Entity-Entity Contexts
1. The entity types provided by the NER
2. The sequence of words between the two entities
3. The part-of-speech tags of these words
4. A flag indicating which entity came first
5. An n-gram to the left of the first entity
6. An n-gram to the right of the second entity
7. A dependency path between the two entities
1 0 0 ... 1
0 1 1 ... 0
1 1 0 ... 0
0 0 0 ... 1
Un,k
∑k,k
Vk,m
Singular Value Decomposition (SVD)
Relational Vector Space Model
LRMn,k
= (Uk
Σk
)n,k
m columns
n rows
Rome is the capital of Italy.
David Gilmour was the guitarist of Pink Floyd.
Pac-Man is an arcade developed by Namco.
...
(Rome, Italy)
(David Gilmour, Pink Floyd)
(Pac-Man, Namco)
...
Use Case: Knowledge Base Population in Cold Start
Rossiello G., Gliozzo A., Fauceglia N. RELATION EXTRACTION FROM A CORPUS USING AN
INFORMATION RETRIEVAL BASED PROCEDURE. Patent ID P201706307
Use Case: Knowledge Base Population in Cold Start
Training examples
Geometric Interpretation of Relations
“A semantic relation R is a region in a relational vector space
LRMn,k
that outlines the boundaries among those entity-pair
vectors that are analogous to each other.”
Dataset: NYT-FB [Riedel, 2010]
New York, Brooklyn
Bill Gates, Microsoft
A:B=C:D ⇔ dist(r(A,B)
,r(C,D)
) <
t
LRM for Distantly Supervised Relation Extraction
Dataset: NTY-FB [Riedel, 2010]
Corpus: New York Times (2005-2007)
KG: Freebase
Relations/classes: 51
Training positive: 4700
Training negative: 63569
Test positive: 1950
Test negative: 94917
LRM: SVD [Halko, 2011] k=2000
Classifier: SVM one-vs-rest
ARES (Ours) = LRM + SVM
Conclusion
● Relation Extraction (RE) as Analogy Problem
(two sides of the same coin)
● Latent Relational Model (LRM) for RE
● Geometric Interpretation of Relations
● LRM for Unsupervised RE
● LRM for Semi-supervised RE
● LRM for Supervised RE
Limitations of LRM / Future Work
● NLP pipeline and SVD do not scale on very large corpora
○ Learning Relational Representations by Analogy
using Hierarchical Siamese Networks [Rossiello et al, NAACL 2019]
○ Variational Autoencoders
● LRM is not able to model the directionality of relations
○ founder(Person, Company) - OK
○ competitor(Company, Company) - OK
○ supplyTo(Company, Company) - KO!
● One entity-entity embedding encodes many relations
○ Contextual Relational Embeddings, like ELMO [Peters, 2018], BERT [Devlin, 2018]
○ Lookup tensor: [entity-entity, mention, vector]
● Extract n-ary Relations
○ Towards Unsupervised Semantic/Frame Parsing
Thank you!

More Related Content

What's hot

Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introductionYueshen Xu
 
Basic review on topic modeling
Basic review on  topic modelingBasic review on  topic modeling
Basic review on topic modelingHiroyuki Kuromiya
 
Language Models for Information Retrieval
Language Models for Information RetrievalLanguage Models for Information Retrieval
Language Models for Information RetrievalNik Spirin
 
Neural Models for Document Ranking
Neural Models for Document RankingNeural Models for Document Ranking
Neural Models for Document RankingBhaskar Mitra
 
Vectorland: Brief Notes from Using Text Embeddings for Search
Vectorland: Brief Notes from Using Text Embeddings for SearchVectorland: Brief Notes from Using Text Embeddings for Search
Vectorland: Brief Notes from Using Text Embeddings for SearchBhaskar Mitra
 
Deep Learning for Search
Deep Learning for SearchDeep Learning for Search
Deep Learning for SearchBhaskar Mitra
 
Neural Information Retrieval: In search of meaningful progress
Neural Information Retrieval: In search of meaningful progressNeural Information Retrieval: In search of meaningful progress
Neural Information Retrieval: In search of meaningful progressBhaskar Mitra
 
Duet @ TREC 2019 Deep Learning Track
Duet @ TREC 2019 Deep Learning TrackDuet @ TREC 2019 Deep Learning Track
Duet @ TREC 2019 Deep Learning TrackBhaskar Mitra
 
Topic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic ModelsTopic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic ModelsClaudia Wagner
 
TopicModels_BleiPaper_Summary.pptx
TopicModels_BleiPaper_Summary.pptxTopicModels_BleiPaper_Summary.pptx
TopicModels_BleiPaper_Summary.pptxKalpit Desai
 
Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...
Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...
Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...Association for Computational Linguistics
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet AllocationMarco Righini
 
Neural Models for Information Retrieval
Neural Models for Information RetrievalNeural Models for Information Retrieval
Neural Models for Information RetrievalBhaskar Mitra
 
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning Track
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning TrackConformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning Track
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning TrackBhaskar Mitra
 
Word Embedding to Document distances
Word Embedding to Document distancesWord Embedding to Document distances
Word Embedding to Document distancesGanesh Borle
 
Latent dirichletallocation presentation
Latent dirichletallocation presentationLatent dirichletallocation presentation
Latent dirichletallocation presentationSoojung Hong
 
A Simple Introduction to Word Embeddings
A Simple Introduction to Word EmbeddingsA Simple Introduction to Word Embeddings
A Simple Introduction to Word EmbeddingsBhaskar Mitra
 
Adversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrievalAdversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrievalBhaskar Mitra
 
Topic model, LDA and all that
Topic model, LDA and all thatTopic model, LDA and all that
Topic model, LDA and all thatZhibo Xiao
 

What's hot (20)

Language models
Language modelsLanguage models
Language models
 
Topic model an introduction
Topic model an introductionTopic model an introduction
Topic model an introduction
 
Basic review on topic modeling
Basic review on  topic modelingBasic review on  topic modeling
Basic review on topic modeling
 
Language Models for Information Retrieval
Language Models for Information RetrievalLanguage Models for Information Retrieval
Language Models for Information Retrieval
 
Neural Models for Document Ranking
Neural Models for Document RankingNeural Models for Document Ranking
Neural Models for Document Ranking
 
Vectorland: Brief Notes from Using Text Embeddings for Search
Vectorland: Brief Notes from Using Text Embeddings for SearchVectorland: Brief Notes from Using Text Embeddings for Search
Vectorland: Brief Notes from Using Text Embeddings for Search
 
Deep Learning for Search
Deep Learning for SearchDeep Learning for Search
Deep Learning for Search
 
Neural Information Retrieval: In search of meaningful progress
Neural Information Retrieval: In search of meaningful progressNeural Information Retrieval: In search of meaningful progress
Neural Information Retrieval: In search of meaningful progress
 
Duet @ TREC 2019 Deep Learning Track
Duet @ TREC 2019 Deep Learning TrackDuet @ TREC 2019 Deep Learning Track
Duet @ TREC 2019 Deep Learning Track
 
Topic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic ModelsTopic Models - LDA and Correlated Topic Models
Topic Models - LDA and Correlated Topic Models
 
TopicModels_BleiPaper_Summary.pptx
TopicModels_BleiPaper_Summary.pptxTopicModels_BleiPaper_Summary.pptx
TopicModels_BleiPaper_Summary.pptx
 
Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...
Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...
Jan Wira Gotama Putra - 2017 - Evaluating Text Coherence Based on Semantic Si...
 
Latent Dirichlet Allocation
Latent Dirichlet AllocationLatent Dirichlet Allocation
Latent Dirichlet Allocation
 
Neural Models for Information Retrieval
Neural Models for Information RetrievalNeural Models for Information Retrieval
Neural Models for Information Retrieval
 
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning Track
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning TrackConformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning Track
Conformer-Kernel with Query Term Independence @ TREC 2020 Deep Learning Track
 
Word Embedding to Document distances
Word Embedding to Document distancesWord Embedding to Document distances
Word Embedding to Document distances
 
Latent dirichletallocation presentation
Latent dirichletallocation presentationLatent dirichletallocation presentation
Latent dirichletallocation presentation
 
A Simple Introduction to Word Embeddings
A Simple Introduction to Word EmbeddingsA Simple Introduction to Word Embeddings
A Simple Introduction to Word Embeddings
 
Adversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrievalAdversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrieval
 
Topic model, LDA and all that
Topic model, LDA and all thatTopic model, LDA and all that
Topic model, LDA and all that
 

Similar to Latent Relational Model for Relation Extraction

Rules for inducing hierarchies from social tagging data
Rules for inducing hierarchies from social tagging dataRules for inducing hierarchies from social tagging data
Rules for inducing hierarchies from social tagging dataHang Dong
 
Effective Semantics for Engineering NLP Systems
Effective Semantics for Engineering NLP SystemsEffective Semantics for Engineering NLP Systems
Effective Semantics for Engineering NLP SystemsAndre Freitas
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Bhaskar Mitra
 
The Geometry of Learning
The Geometry of LearningThe Geometry of Learning
The Geometry of Learningfridolin.wild
 
More ways of symbol grounding for knowledge graphs?
More ways of symbol grounding for knowledge graphs?More ways of symbol grounding for knowledge graphs?
More ways of symbol grounding for knowledge graphs?Paul Groth
 
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts Saeedeh Shekarpour
 
Contextual Ontology Alignment - ESWC 2011
Contextual Ontology Alignment - ESWC 2011Contextual Ontology Alignment - ESWC 2011
Contextual Ontology Alignment - ESWC 2011Mariana Damova, Ph.D
 
The Essay Scoring Tool (TEST) for Hindi
The Essay Scoring Tool (TEST) for HindiThe Essay Scoring Tool (TEST) for Hindi
The Essay Scoring Tool (TEST) for Hindisinghg77
 
Interactive Analysis of Word Vector Embeddings
Interactive Analysis of Word Vector EmbeddingsInteractive Analysis of Word Vector Embeddings
Interactive Analysis of Word Vector Embeddingsgleicher
 
Neural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain ShiftNeural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain ShiftSebastian Ruder
 
Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Andre Freitas
 
AI Beyond Deep Learning
AI Beyond Deep LearningAI Beyond Deep Learning
AI Beyond Deep LearningAndre Freitas
 
Natural language processing and transformer models
Natural language processing and transformer modelsNatural language processing and transformer models
Natural language processing and transformer modelsDing Li
 
Explanations in Dialogue Systems through Uncertain RDF Knowledge Bases
Explanations in Dialogue Systems through Uncertain RDF Knowledge BasesExplanations in Dialogue Systems through Uncertain RDF Knowledge Bases
Explanations in Dialogue Systems through Uncertain RDF Knowledge BasesDaniel Sonntag
 
Data Tactics Data Science Brown Bag (April 2014)
Data Tactics Data Science Brown Bag (April 2014)Data Tactics Data Science Brown Bag (April 2014)
Data Tactics Data Science Brown Bag (April 2014)Rich Heimann
 
Data Science and Analytics Brown Bag
Data Science and Analytics Brown BagData Science and Analytics Brown Bag
Data Science and Analytics Brown BagDataTactics
 
Lean Logic for Lean Times: Varieties of Natural Logic
Lean Logic for Lean Times: Varieties of Natural LogicLean Logic for Lean Times: Varieties of Natural Logic
Lean Logic for Lean Times: Varieties of Natural LogicValeria de Paiva
 
Detecting paraphrases using recursive autoencoders
Detecting paraphrases using recursive autoencodersDetecting paraphrases using recursive autoencoders
Detecting paraphrases using recursive autoencodersFeynman Liang
 
Contextual ontology alignment may 2011
Contextual ontology alignment may 2011Contextual ontology alignment may 2011
Contextual ontology alignment may 2011Mariana Damova, Ph.D
 
Survey of Generative Clustering Models 2008
Survey of Generative Clustering Models 2008Survey of Generative Clustering Models 2008
Survey of Generative Clustering Models 2008Roman Stanchak
 

Similar to Latent Relational Model for Relation Extraction (20)

Rules for inducing hierarchies from social tagging data
Rules for inducing hierarchies from social tagging dataRules for inducing hierarchies from social tagging data
Rules for inducing hierarchies from social tagging data
 
Effective Semantics for Engineering NLP Systems
Effective Semantics for Engineering NLP SystemsEffective Semantics for Engineering NLP Systems
Effective Semantics for Engineering NLP Systems
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)
 
The Geometry of Learning
The Geometry of LearningThe Geometry of Learning
The Geometry of Learning
 
More ways of symbol grounding for knowledge graphs?
More ways of symbol grounding for knowledge graphs?More ways of symbol grounding for knowledge graphs?
More ways of symbol grounding for knowledge graphs?
 
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
 
Contextual Ontology Alignment - ESWC 2011
Contextual Ontology Alignment - ESWC 2011Contextual Ontology Alignment - ESWC 2011
Contextual Ontology Alignment - ESWC 2011
 
The Essay Scoring Tool (TEST) for Hindi
The Essay Scoring Tool (TEST) for HindiThe Essay Scoring Tool (TEST) for Hindi
The Essay Scoring Tool (TEST) for Hindi
 
Interactive Analysis of Word Vector Embeddings
Interactive Analysis of Word Vector EmbeddingsInteractive Analysis of Word Vector Embeddings
Interactive Analysis of Word Vector Embeddings
 
Neural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain ShiftNeural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain Shift
 
Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...
 
AI Beyond Deep Learning
AI Beyond Deep LearningAI Beyond Deep Learning
AI Beyond Deep Learning
 
Natural language processing and transformer models
Natural language processing and transformer modelsNatural language processing and transformer models
Natural language processing and transformer models
 
Explanations in Dialogue Systems through Uncertain RDF Knowledge Bases
Explanations in Dialogue Systems through Uncertain RDF Knowledge BasesExplanations in Dialogue Systems through Uncertain RDF Knowledge Bases
Explanations in Dialogue Systems through Uncertain RDF Knowledge Bases
 
Data Tactics Data Science Brown Bag (April 2014)
Data Tactics Data Science Brown Bag (April 2014)Data Tactics Data Science Brown Bag (April 2014)
Data Tactics Data Science Brown Bag (April 2014)
 
Data Science and Analytics Brown Bag
Data Science and Analytics Brown BagData Science and Analytics Brown Bag
Data Science and Analytics Brown Bag
 
Lean Logic for Lean Times: Varieties of Natural Logic
Lean Logic for Lean Times: Varieties of Natural LogicLean Logic for Lean Times: Varieties of Natural Logic
Lean Logic for Lean Times: Varieties of Natural Logic
 
Detecting paraphrases using recursive autoencoders
Detecting paraphrases using recursive autoencodersDetecting paraphrases using recursive autoencoders
Detecting paraphrases using recursive autoencoders
 
Contextual ontology alignment may 2011
Contextual ontology alignment may 2011Contextual ontology alignment may 2011
Contextual ontology alignment may 2011
 
Survey of Generative Clustering Models 2008
Survey of Generative Clustering Models 2008Survey of Generative Clustering Models 2008
Survey of Generative Clustering Models 2008
 

Recently uploaded

Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
TOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxTOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxdharshini369nike
 
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaDashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaPraksha3
 
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxTwin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxEran Akiva Sinbar
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxmalonesandreagweneth
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
Cytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxCytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxVarshiniMK
 
Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2John Carlo Rollon
 
Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫qfactory1
 
Forest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantForest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantadityabhardwaj282
 
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRlizamodels9
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trssuser06f238
 
Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)DHURKADEVIBASKAR
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024AyushiRastogi48
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsHajira Mahmood
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsCharlene Llagas
 

Recently uploaded (20)

Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Munirka Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Aiims Metro Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
TOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptxTOTAL CHOLESTEROL (lipid profile test).pptx
TOTAL CHOLESTEROL (lipid profile test).pptx
 
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaDashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
 
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptxTwin's paradox experiment is a meassurement of the extra dimensions.pptx
Twin's paradox experiment is a meassurement of the extra dimensions.pptx
 
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptxLIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
Cytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxCytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptx
 
Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2Evidences of Evolution General Biology 2
Evidences of Evolution General Biology 2
 
Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫
 
Forest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are importantForest laws, Indian forest laws, why they are important
Forest laws, Indian forest laws, why they are important
 
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 tr
 
Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutions
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of Traits
 

Latent Relational Model for Relation Extraction

  • 1. Latent Relational Model for Relation Extraction Gaetano Rossiello1 , Alfio Gliozzo2 , Nicolas Fauceglia2 , Giovanni Semeraro1 1 Department of Computer Science - University of Bari, Italy 2 IBM Research AI - Yorktown Heights, NY, USA gaetano.rossiello@uniba.it github.com/gaetangate /in/gaetano-rossiello @tanoross
  • 2. Goal: from Text to Knowledge Unstructured Textual Data Structured Data Knowledge & Insights ● Information Extraction ○ Entity Recognition ○ Relation Extraction ● Frame Parsing ● Semantic Parsing ○ FOL ○ Lambda Calculus ○ AMR ● Deductive Reasoning ● Inductive Logic Programming ● Probabilistic (Logic) Programming ● Relational Embeddings ● ...
  • 3. Why Relation Extraction? ● Automatic Knowledge Base Population (AKBP) ○ Lexical resources: add words to WordNet thesaurus ○ Fact bases: add facts to Wikidata or DBpedia ● Automatic Knowledge Base Construction (AKBC) ● Sample application: Question Answering (QA) ○ Who are the actors younger than Tom Hanks? (isA ?x actor) (birthDate ?x ?y) (birthDate “Tom_Hanks” ?z) (> ?y ?z)
  • 4. Relation Extraction Approaches ● Pattern-based [Hearst, 1992] ○ Hand-crafted rules ● Bootstrapping [Agichtein, 2000] ○ Semantic drift ● OpenIE [Banko, 2007; Fader, 2011; Mausam, 2012] ○ Lexicalized relations not in a canonical form ● Supervised [Jiang, 2007; Sun, 2014; Nguyen, 2015] ○ Manually annotated training examples ● Distant Supervision [Mintz, 2009; Lin, 2016; Glass, 2018] ○ An existing KB is used to generate training examples ○ Advantages from both bootstrapping and supervised RE
  • 5. ISWC Semantic Web Challenge 2017 Glass, M., Gliozzo, A., Hassanzadeh, O., Mihindukulasooriya, N., Rossiello, G. Inducing implicit relations from text using distantly supervised deep nets. ISWC 2018. PCNN-KI: Piecewise Convolutional Neural Network for Distantly Supervised RE PermID KG
  • 6. Distantly Supervised RE: Limitations ● Distant Supervision does not fit well for vertical domains or long-tailed relation types, where only a few seed examples are available ● The generalization capability is limited only to those relation types seen during the training phase Distantly supervised RE cannot be applied in other domains with new relation types
  • 7. Use Case: Knowledge Base Population in Cold Start Research Question: How to design a method able to identify new relation types in a (small) collection of documents using a few examples? Training examples
  • 8. Relation Extraction as Analogy Problem ● Given a corpus D and an entity pair (a, b) ● Find the set R = {(x, y) ∊ D | a : b = x : y} Watson : IBM = Pixel : Google Query pair Result pair
  • 9. Word Analogy using Distributional Semantic Models Vector offset with Word Embeddings man : king = woman : ? vec(king) - vec(man) + vec (woman) ≈ vec(queen) vec(king) - vec(man) ≈ vec(queen) - vec(woman) Mikolov, T., Chen, K., Corrado, G., & Dean, J. Efficient estimation of word representations in vector space. ICLR 2013. Pennington, J., Socher, R., & Manning, C. D. Glove: Global vectors for word representation. EMNLP 2014. Levy, O., Goldberg, Y., & Dagan, I. Improving distributional similarity with lessons learned from word embeddings. TACL 2015. Limitations: ● Handling multi-word (e.g. Tom Hanks) with pre-trained word embedding models ● Handling unseen words/entities ● Not effective on SAT Analogy Questions [Church, 2017]
  • 10. SAT Analogy Questions Dataset ● SAT = Scholastic Aptitude Test [Turney, 2003] ● 374 multiple-choice analogy questions; 5 choices per question ● Human performance: 81.5% ● SOTA - Latent Relational Analysis (LRA): 56.1% Turney, P.D., and Littman, M.L. Corpus-based learning of analogies and semantic relations. Machine Learning. 2005. Turney, P.D. Similarity of semantic relations. Computational Linguistics. 2006. LRA r1 = vec(mason:stone) r2 = vec(carpenter:wood) sim = cosine(r1, r2)
  • 11. Latent Relational Model for RE Entity-Entity Vocabulary V = {(X1, Y1),..., (Xn, Yn)} Entity-Entity Contexts 1. The entity types provided by the NER 2. The sequence of words between the two entities 3. The part-of-speech tags of these words 4. A flag indicating which entity came first 5. An n-gram to the left of the first entity 6. An n-gram to the right of the second entity 7. A dependency path between the two entities 1 0 0 ... 1 0 1 1 ... 0 1 1 0 ... 0 0 0 0 ... 1 Un,k ∑k,k Vk,m Singular Value Decomposition (SVD) Relational Vector Space Model LRMn,k = (Uk Σk )n,k m columns n rows Rome is the capital of Italy. David Gilmour was the guitarist of Pink Floyd. Pac-Man is an arcade developed by Namco. ... (Rome, Italy) (David Gilmour, Pink Floyd) (Pac-Man, Namco) ...
  • 12. Use Case: Knowledge Base Population in Cold Start Rossiello G., Gliozzo A., Fauceglia N. RELATION EXTRACTION FROM A CORPUS USING AN INFORMATION RETRIEVAL BASED PROCEDURE. Patent ID P201706307
  • 13. Use Case: Knowledge Base Population in Cold Start Training examples
  • 14. Geometric Interpretation of Relations “A semantic relation R is a region in a relational vector space LRMn,k that outlines the boundaries among those entity-pair vectors that are analogous to each other.” Dataset: NYT-FB [Riedel, 2010] New York, Brooklyn Bill Gates, Microsoft A:B=C:D ⇔ dist(r(A,B) ,r(C,D) ) < t
  • 15. LRM for Distantly Supervised Relation Extraction Dataset: NTY-FB [Riedel, 2010] Corpus: New York Times (2005-2007) KG: Freebase Relations/classes: 51 Training positive: 4700 Training negative: 63569 Test positive: 1950 Test negative: 94917 LRM: SVD [Halko, 2011] k=2000 Classifier: SVM one-vs-rest ARES (Ours) = LRM + SVM
  • 16. Conclusion ● Relation Extraction (RE) as Analogy Problem (two sides of the same coin) ● Latent Relational Model (LRM) for RE ● Geometric Interpretation of Relations ● LRM for Unsupervised RE ● LRM for Semi-supervised RE ● LRM for Supervised RE
  • 17. Limitations of LRM / Future Work ● NLP pipeline and SVD do not scale on very large corpora ○ Learning Relational Representations by Analogy using Hierarchical Siamese Networks [Rossiello et al, NAACL 2019] ○ Variational Autoencoders ● LRM is not able to model the directionality of relations ○ founder(Person, Company) - OK ○ competitor(Company, Company) - OK ○ supplyTo(Company, Company) - KO! ● One entity-entity embedding encodes many relations ○ Contextual Relational Embeddings, like ELMO [Peters, 2018], BERT [Devlin, 2018] ○ Lookup tensor: [entity-entity, mention, vector] ● Extract n-ary Relations ○ Towards Unsupervised Semantic/Frame Parsing