SlideShare uma empresa Scribd logo
1 de 29
K-SRL: Instance-based
Learning for Semantic Role
Labeling
Alan Akbik and Yunyao Li
IBM Research | Almaden
COLING 2016, 12/13/2016
SystemT
In Short
• K-SRL utilizes a simple but effective approach for
SRL
– Instance-based learning
– kNN: k-nearest neighbors
• State-of-the-art
– CoNLL-09 shared task data
– Outperforms previous SotA systems based on logistic regression and
NNs
– Both in-domain and out-of-domain data
2
Outline
• Problem Statement
• Proposed Approach
• Evaluation
• Discussion
SRL focuses on semantics, not syntax
Useful for many applications (Shen and
Lapata, 2007; Maqsud et al., 2014)
Dirk broke the window with a hammer.
Break.01A0 A1 A2
The window was broken by Dirk.
The window broke.
A1 Break.01 A0
A1 Break.01
Break.01
A0 – Breaker
A1 – Thing broken
A2 – Instrument
A3 – Pieces
Break.15
A0 – Journalist,
exposer
A1 – Story,
thing exposed
• Identify predicate-argument structures in sentences with
shallow semantic labels
• Identify which predicates evoke which semantic frames
• Identify constituents that take semantic roles within these frames
Semantic Role Labeling
SRL for NLP tasks
• Question Answering
– “What did Dirk break?”
– (Maqsud et al., 2014)
• Information Extraction
– “Who wants to buy what?”
– (Shen and Lapata, 2007)
• At IBM Research:
– Multilingual SRL
– Multilingual text analytics
5
SRL vs. Dependency Parsing
• LAS of state-of-the-art dependency parsers
– 92.05 (Weiss et al, 2015)
– 92.36 (Alberti et al, 2015)
– 92.79 (Andor et al, 2016)
• F1 of state-of-the-art SRL
– 87.79 (Roth and Woodsend, 2014)
– 88.19 (Roth and Lapata, 2016)
• SotA SRL quality lower than SotA dependency
parsing
6
SRL Challenges
• So, what makes SRL so difficult?
• Heavy-tailed distribution of class labels
– Common frames
• say.01 (8243), have.01 (2040), sell.01 (1009)
– Many uncommon frames
• swindle.01, feed.01, hum.01, toast.01
– Almost half of all frames seen fewer than 3 times in training data
• Many low-frequency exceptions
– Difficult to capture in model
7
0
2000
4000
6000
8000
10000
Distribution of frame labels
Low-frequency Exceptions
• Strong correlation of syntactic function of an argument to its role
• Example: passive subject
• CoNLL-09 Shared Task data:
– 86% of passive subjects are labeled A1
– Remaining 14% irregular, low-frequency exceptions
8
The window was broken by Dirk
SBJ
PMOD
VC NMOD
A1
The silver was sold by the man.
SBJ
PMOD
VC NMOD
A1
Creditors were told to hold off.
SBJ
ORPD
VC
IM PRT
TELL.01
A0: speaker (agent)
A1: utterance (topic)
A2: hearer (recipient)
Local Bias
• 86% of passive subjects are labeled A1 (over 4.000x in training
data)
• 87% of passive subjects of Tell.01 are labeled A2 (53x in training
data)
• Most classifiers:
– Bag-of-features
– Learn weights for features to classes
– Perform generalization
• Question: How do we explicitly capture low-frequency exceptions?
9
Outline
• Problem Statement
• Proposed Approach
• Evaluation
• Discussion
Instance-based Learning
• Proposed approach: Instance-based learning
– kNN: k-Nearest Neighbors classification
– Find the k most similar instances in training data
– Derive class label from nearest neighbors
11
A0
A1
A1
A2
A1
A1
A1
A1
A1
A0
A0
A1
A0
A2
A2A2
A2
A1
A2
?
1 2 3 ndistance
Creditors were told to hold off.
SBJ
ORPD
VC
IM PRT
“creditor” passive subject of TELL.01
noun passive subject of TELL.01
COMPOSITE FEATURE DISTANCE
1
2
.
.
.
.
.
.
any passive subject of any agentive verb n
?
– Main idea: Back off to composite feature seen at least k times
System Outline
• kNN classifier for both tasks
– Predicate labeling: Subcategorization features (subject, object, PPs)
– Argument labeling: Predicate frame, predicate POS, predicate voice, argument
head lemma, argument head POS, syntactic function of argument
• Additionally model global argument constraints
– Easy-First Argument Labeling
12
1. PREDICATE LABELING
2. ARGUMENT LABELING
Creditors were told to hold off.
TELL.01
A2 A1 A0
HOLD.01
Easy-First Argument Labeling
• Core roles can only be assigned once per predicate
13
Creditors were told to hold off.
Interesting stories were told to creditors.
TELL.01
A0: speaker (agent)
A1: utterance (topic)
A2: hearer (recipient)
A2 – 86%
A1 – 14%
A2 – 86%
A1 – 14%
A2 – 100%
• Easy-first:
– Order argument classifications by confidence
– Make most confident prediction first
– Remove assigned labels from options
Outline
• Problem Statement
• Proposed Approach
• Evaluation
• Discussion
Evaluation
• Comparison to previous SotA approaches:
– Chen(Zhao et al., 2009), maximum entropy
– Che(Che et al., 2009), support vector machines
– MatePlus(Roth and Woodsend, 2014), logistic regression and word embeddings
– PathLSTM (Roth and Lapata, 2016), logistic regression for predicates and NNs
with word embeddings for arguments
• Additional questions:
– Impact of choice of k?
– Overfitting?
– Impact of modeling global argument constraints?
• Dataset: CoNLL-09 Shared Task data
– Penn treebank w. PropBank SRL annotations
– NomBank annotations not evaluated
– Out-of-domain data: Brown corpus
15
Results
16
In-domain Out-of-domain
Results
• Significantly outperform previous approaches
– Especially on out-of-domain data
• Small neighborhoods suffice
• Very simple feature set
– No word embeddings or verb classes
17
Discussion
• Pros:
– Simple, highly transparent classification approach
• Composite features make feature interactions explicit
• Nearest neighborhood makes classification decision transparent
– Very fast to train and test
– Fast and transparent: Great for feature engineering
• Cons:
– IBL necessitates more feature engineering
• Define composites
• “Rank” composites into backoff sequences
18
Current and Future Work
• Learning instance similarity measures
– Manual definition of composites, but automatic ranking
– Improves quality over published numbers
• Better generalization features
– Word-level: Embeddings
– Predicate-level: “Frame classes”
• Special focus on raised arguments
19
The man broke the window.
SBJ OBJ
A0
The rock broke the window.
SBJ OBJ
A2
Creditors were told to hold off.
SBJ
ORPD
VC
IM PRT
Current Related Work at IBM Research
• Multilingual SRL
– Creating “Universal Proposition Banks” on top of Universal
Dependencies
– Version 1.0 released: https://github.com/System-
T/UniversalPropositions/
– COLING paper “Multilingual Aliasing for Auto-Generating
Proposition Banks”
• Poster session on Friday
• Multilingual text analytics
– COLING demo “Multilingual Information Extraction with
PolyglotIE”
• Demo session on Friday
20
Questions?
21
22
• Problem: Current SRL error-prone
• Strong local bias
• Many low-frequency exceptions, difficult to generalize
23
Instance-based Semantic Role Labeling
• K-SRL: Instance-based
learning
– K-nearest neighbors
• Composite features
• Significantly outperform all
other current systems
In-domain Out-of-domain
Instance-based Learning
• Most ML algorithms
– Bag of features: Syntactic function, predicate, voice …
– Learn weights for features to classes
• Strong weight for “passive subject” to A1
– Perform generalization
• Proposed approach: Instance-based learning
– kNN: k-Nearest Neighbors classification
– Find the k most similar instances in training data
• “all instances in which argument is a passive subject of TELL.01”
• Derive class label from majority in neighborhood
– No generalization
– Explicitly capture local bias using composite features
24
• Problem: Current SRL error-prone
• Strong local bias, many low-frequency exceptions, difficult to
generalize
25
Instance-based Semantic Role Labeling
Composite Features and Support
26
Creditors were told to hold off.
SBJ
ORPD
VC
IM PRT
TELL.01
A0: speaker (agent)
A1: utterance (topic)
A2: hearer (recipient)
voice (V): passive
predicate (P): tell
path (P): VC SBJ
ActionAPI - Demo
27
28
John hastily ordered a dozen dandelions for Mary from Amazon’s Flower Shop.
order.02 (request to be delivered)
A0: Orderer
A1: Thing ordered
A2: Benefactive, ordered-for
A3: Source
A0: Orderer
A1: Thing ordered
A2: Benefactive, ordered-for
A3: SourceAM-MNR: Manner
SRL: Who did what to whom, when,
where and how?
WHO
HOW
FOR
WHOM
DID
WHAT WHERE
• Problem: What type of labels are valid across
languages?
• Lexical, morphological and syntactic labels differ greatly
• But shallow semantic labels remain stable
Core idea: Predict English Semantic Role Labels for
arbitrary languages
Semantic Role Labeling
The station bought Cosby reruns for record prices
Buy.01A0
… spurred dollar buying by Japanese institutions.
Spur.01 A1 Buy.01 A0
The company payed 2 million US$ to buy ….
Corpus of annotated text dataFrame set
A1 A3
Buy.01
A0 – Buyer
A1 – Thing bought
A2 – Seller
A3 – Price paid
A4 – Benefactive
Pay.01
A0 – Payer
A1 – Money
A2 – Being payed
A3 – Commodity
Buy.01Pay.01A0 A1
• English SRL
– FrameNet
– PropBank
SRL Resources

Mais conteúdo relacionado

Semelhante a K-SRL: Instance-based Learning for Semantic Role Labeling

One talk Machine Learning
One talk Machine LearningOne talk Machine Learning
One talk Machine LearningONE Talks
 
Training machine learning knn 2017
Training machine learning knn 2017Training machine learning knn 2017
Training machine learning knn 2017Iwan Sofana
 
Seminar on Parallel and Concurrent Programming
Seminar on Parallel and Concurrent ProgrammingSeminar on Parallel and Concurrent Programming
Seminar on Parallel and Concurrent ProgrammingStefan Marr
 
Efficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databasesEfficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databasesRui Vieira
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueTransformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueJinho Choi
 
Artificial Intelligence: Knowledge Acquisition
Artificial Intelligence: Knowledge AcquisitionArtificial Intelligence: Knowledge Acquisition
Artificial Intelligence: Knowledge AcquisitionThe Integral Worm
 
Different Semantic Perspectives for Question Answering Systems
Different Semantic Perspectives for Question Answering SystemsDifferent Semantic Perspectives for Question Answering Systems
Different Semantic Perspectives for Question Answering SystemsAndre Freitas
 
Local vs. Global Models for Effort Estimation and Defect Prediction
Local vs. Global Models for Effort Estimation and Defect Prediction Local vs. Global Models for Effort Estimation and Defect Prediction
Local vs. Global Models for Effort Estimation and Defect Prediction CS, NcState
 
Query dependent ranking using k nearest neighbor
Query dependent ranking using k nearest neighborQuery dependent ranking using k nearest neighbor
Query dependent ranking using k nearest neighboriyo
 
Big learning 1.2
Big learning   1.2Big learning   1.2
Big learning 1.2Mohit Garg
 
Grosof haley-talk-semtech2013-ver6-10-13
Grosof haley-talk-semtech2013-ver6-10-13Grosof haley-talk-semtech2013-ver6-10-13
Grosof haley-talk-semtech2013-ver6-10-13Brian Ulicny
 
big data analytics.pptx
big data analytics.pptxbig data analytics.pptx
big data analytics.pptxSabthamiS1
 

Semelhante a K-SRL: Instance-based Learning for Semantic Role Labeling (20)

One talk Machine Learning
One talk Machine LearningOne talk Machine Learning
One talk Machine Learning
 
Training machine learning knn 2017
Training machine learning knn 2017Training machine learning knn 2017
Training machine learning knn 2017
 
Seminar on Parallel and Concurrent Programming
Seminar on Parallel and Concurrent ProgrammingSeminar on Parallel and Concurrent Programming
Seminar on Parallel and Concurrent Programming
 
KNN
KNNKNN
KNN
 
Efficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databasesEfficient top-k queries processing in column-family distributed databases
Efficient top-k queries processing in column-family distributed databases
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueTransformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
 
asdrfasdfasdf
asdrfasdfasdfasdrfasdfasdf
asdrfasdfasdf
 
Artificial Intelligence: Knowledge Acquisition
Artificial Intelligence: Knowledge AcquisitionArtificial Intelligence: Knowledge Acquisition
Artificial Intelligence: Knowledge Acquisition
 
Different Semantic Perspectives for Question Answering Systems
Different Semantic Perspectives for Question Answering SystemsDifferent Semantic Perspectives for Question Answering Systems
Different Semantic Perspectives for Question Answering Systems
 
semantic web & natural language
semantic web & natural languagesemantic web & natural language
semantic web & natural language
 
Seminar dm
Seminar dmSeminar dm
Seminar dm
 
social.pptx
social.pptxsocial.pptx
social.pptx
 
Clustering - ACM 2013 02-25
Clustering - ACM 2013 02-25Clustering - ACM 2013 02-25
Clustering - ACM 2013 02-25
 
N20190729
N20190729N20190729
N20190729
 
Local vs. Global Models for Effort Estimation and Defect Prediction
Local vs. Global Models for Effort Estimation and Defect Prediction Local vs. Global Models for Effort Estimation and Defect Prediction
Local vs. Global Models for Effort Estimation and Defect Prediction
 
Query dependent ranking using k nearest neighbor
Query dependent ranking using k nearest neighborQuery dependent ranking using k nearest neighbor
Query dependent ranking using k nearest neighbor
 
Lecture2-DT.pptx
Lecture2-DT.pptxLecture2-DT.pptx
Lecture2-DT.pptx
 
Big learning 1.2
Big learning   1.2Big learning   1.2
Big learning 1.2
 
Grosof haley-talk-semtech2013-ver6-10-13
Grosof haley-talk-semtech2013-ver6-10-13Grosof haley-talk-semtech2013-ver6-10-13
Grosof haley-talk-semtech2013-ver6-10-13
 
big data analytics.pptx
big data analytics.pptxbig data analytics.pptx
big data analytics.pptx
 

Mais de Yunyao Li

The Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language ModelsYunyao Li
 
Building, Growing and Serving Large Knowledge Graphs with Human-in-the-Loop
Building, Growing and Serving Large Knowledge Graphs with Human-in-the-LoopBuilding, Growing and Serving Large Knowledge Graphs with Human-in-the-Loop
Building, Growing and Serving Large Knowledge Graphs with Human-in-the-LoopYunyao Li
 
Meaning Representations for Natural Languages: Design, Models and Applications
Meaning Representations for Natural Languages:  Design, Models and ApplicationsMeaning Representations for Natural Languages:  Design, Models and Applications
Meaning Representations for Natural Languages: Design, Models and ApplicationsYunyao Li
 
Taming the Wild West of NLP
Taming the Wild West of NLPTaming the Wild West of NLP
Taming the Wild West of NLPYunyao Li
 
Towards Deep Table Understanding
Towards Deep Table UnderstandingTowards Deep Table Understanding
Towards Deep Table UnderstandingYunyao Li
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language ProcessingYunyao Li
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language ProcessingYunyao Li
 
Human in the Loop AI for Building Knowledge Bases
Human in the Loop AI for Building Knowledge Bases Human in the Loop AI for Building Knowledge Bases
Human in the Loop AI for Building Knowledge Bases Yunyao Li
 
Towards Universal Language Understanding
Towards Universal Language UnderstandingTowards Universal Language Understanding
Towards Universal Language UnderstandingYunyao Li
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language ProcessingYunyao Li
 
Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)Yunyao Li
 
Towards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural LanguagesTowards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural LanguagesYunyao Li
 
An In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social MediaAn In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social MediaYunyao Li
 
Exploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active LearningExploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active LearningYunyao Li
 
Coling poster
Coling posterColing poster
Coling posterYunyao Li
 
Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...Yunyao Li
 
Polyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified LabelsPolyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified LabelsYunyao Li
 
Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...Yunyao Li
 
The Power of Declarative Analytics
The Power of Declarative AnalyticsThe Power of Declarative Analytics
The Power of Declarative AnalyticsYunyao Li
 

Mais de Yunyao Li (20)

The Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language Models
 
Building, Growing and Serving Large Knowledge Graphs with Human-in-the-Loop
Building, Growing and Serving Large Knowledge Graphs with Human-in-the-LoopBuilding, Growing and Serving Large Knowledge Graphs with Human-in-the-Loop
Building, Growing and Serving Large Knowledge Graphs with Human-in-the-Loop
 
Meaning Representations for Natural Languages: Design, Models and Applications
Meaning Representations for Natural Languages:  Design, Models and ApplicationsMeaning Representations for Natural Languages:  Design, Models and Applications
Meaning Representations for Natural Languages: Design, Models and Applications
 
Taming the Wild West of NLP
Taming the Wild West of NLPTaming the Wild West of NLP
Taming the Wild West of NLP
 
Towards Deep Table Understanding
Towards Deep Table UnderstandingTowards Deep Table Understanding
Towards Deep Table Understanding
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language Processing
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language Processing
 
Human in the Loop AI for Building Knowledge Bases
Human in the Loop AI for Building Knowledge Bases Human in the Loop AI for Building Knowledge Bases
Human in the Loop AI for Building Knowledge Bases
 
Towards Universal Language Understanding
Towards Universal Language UnderstandingTowards Universal Language Understanding
Towards Universal Language Understanding
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language Processing
 
Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)Towards Universal Language Understanding (2020 version)
Towards Universal Language Understanding (2020 version)
 
Towards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural LanguagesTowards Universal Semantic Understanding of Natural Languages
Towards Universal Semantic Understanding of Natural Languages
 
An In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social MediaAn In-depth Analysis of the Effect of Text Normalization in Social Media
An In-depth Analysis of the Effect of Text Normalization in Social Media
 
Exploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active LearningExploiting Structure in Representation of Named Entities using Active Learning
Exploiting Structure in Representation of Named Entities using Active Learning
 
Coling poster
Coling posterColing poster
Coling poster
 
Coling demo
Coling demoColing demo
Coling demo
 
Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...Natural Language Data Management and Interfaces: Recent Development and Open ...
Natural Language Data Management and Interfaces: Recent Development and Open ...
 
Polyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified LabelsPolyglot: Multilingual Semantic Role Labeling with Unified Labels
Polyglot: Multilingual Semantic Role Labeling with Unified Labels
 
Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...Transparent Machine Learning for Information Extraction: State-of-the-Art and...
Transparent Machine Learning for Information Extraction: State-of-the-Art and...
 
The Power of Declarative Analytics
The Power of Declarative AnalyticsThe Power of Declarative Analytics
The Power of Declarative Analytics
 

Último

Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamUiPathCommunity
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfOverkill Security
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024The Digital Insurer
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Zilliz
 

Último (20)

Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdf
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 

K-SRL: Instance-based Learning for Semantic Role Labeling

  • 1. K-SRL: Instance-based Learning for Semantic Role Labeling Alan Akbik and Yunyao Li IBM Research | Almaden COLING 2016, 12/13/2016 SystemT
  • 2. In Short • K-SRL utilizes a simple but effective approach for SRL – Instance-based learning – kNN: k-nearest neighbors • State-of-the-art – CoNLL-09 shared task data – Outperforms previous SotA systems based on logistic regression and NNs – Both in-domain and out-of-domain data 2
  • 3. Outline • Problem Statement • Proposed Approach • Evaluation • Discussion
  • 4. SRL focuses on semantics, not syntax Useful for many applications (Shen and Lapata, 2007; Maqsud et al., 2014) Dirk broke the window with a hammer. Break.01A0 A1 A2 The window was broken by Dirk. The window broke. A1 Break.01 A0 A1 Break.01 Break.01 A0 – Breaker A1 – Thing broken A2 – Instrument A3 – Pieces Break.15 A0 – Journalist, exposer A1 – Story, thing exposed • Identify predicate-argument structures in sentences with shallow semantic labels • Identify which predicates evoke which semantic frames • Identify constituents that take semantic roles within these frames Semantic Role Labeling
  • 5. SRL for NLP tasks • Question Answering – “What did Dirk break?” – (Maqsud et al., 2014) • Information Extraction – “Who wants to buy what?” – (Shen and Lapata, 2007) • At IBM Research: – Multilingual SRL – Multilingual text analytics 5
  • 6. SRL vs. Dependency Parsing • LAS of state-of-the-art dependency parsers – 92.05 (Weiss et al, 2015) – 92.36 (Alberti et al, 2015) – 92.79 (Andor et al, 2016) • F1 of state-of-the-art SRL – 87.79 (Roth and Woodsend, 2014) – 88.19 (Roth and Lapata, 2016) • SotA SRL quality lower than SotA dependency parsing 6
  • 7. SRL Challenges • So, what makes SRL so difficult? • Heavy-tailed distribution of class labels – Common frames • say.01 (8243), have.01 (2040), sell.01 (1009) – Many uncommon frames • swindle.01, feed.01, hum.01, toast.01 – Almost half of all frames seen fewer than 3 times in training data • Many low-frequency exceptions – Difficult to capture in model 7 0 2000 4000 6000 8000 10000 Distribution of frame labels
  • 8. Low-frequency Exceptions • Strong correlation of syntactic function of an argument to its role • Example: passive subject • CoNLL-09 Shared Task data: – 86% of passive subjects are labeled A1 – Remaining 14% irregular, low-frequency exceptions 8 The window was broken by Dirk SBJ PMOD VC NMOD A1 The silver was sold by the man. SBJ PMOD VC NMOD A1 Creditors were told to hold off. SBJ ORPD VC IM PRT TELL.01 A0: speaker (agent) A1: utterance (topic) A2: hearer (recipient)
  • 9. Local Bias • 86% of passive subjects are labeled A1 (over 4.000x in training data) • 87% of passive subjects of Tell.01 are labeled A2 (53x in training data) • Most classifiers: – Bag-of-features – Learn weights for features to classes – Perform generalization • Question: How do we explicitly capture low-frequency exceptions? 9
  • 10. Outline • Problem Statement • Proposed Approach • Evaluation • Discussion
  • 11. Instance-based Learning • Proposed approach: Instance-based learning – kNN: k-Nearest Neighbors classification – Find the k most similar instances in training data – Derive class label from nearest neighbors 11 A0 A1 A1 A2 A1 A1 A1 A1 A1 A0 A0 A1 A0 A2 A2A2 A2 A1 A2 ? 1 2 3 ndistance Creditors were told to hold off. SBJ ORPD VC IM PRT “creditor” passive subject of TELL.01 noun passive subject of TELL.01 COMPOSITE FEATURE DISTANCE 1 2 . . . . . . any passive subject of any agentive verb n ? – Main idea: Back off to composite feature seen at least k times
  • 12. System Outline • kNN classifier for both tasks – Predicate labeling: Subcategorization features (subject, object, PPs) – Argument labeling: Predicate frame, predicate POS, predicate voice, argument head lemma, argument head POS, syntactic function of argument • Additionally model global argument constraints – Easy-First Argument Labeling 12 1. PREDICATE LABELING 2. ARGUMENT LABELING Creditors were told to hold off. TELL.01 A2 A1 A0 HOLD.01
  • 13. Easy-First Argument Labeling • Core roles can only be assigned once per predicate 13 Creditors were told to hold off. Interesting stories were told to creditors. TELL.01 A0: speaker (agent) A1: utterance (topic) A2: hearer (recipient) A2 – 86% A1 – 14% A2 – 86% A1 – 14% A2 – 100% • Easy-first: – Order argument classifications by confidence – Make most confident prediction first – Remove assigned labels from options
  • 14. Outline • Problem Statement • Proposed Approach • Evaluation • Discussion
  • 15. Evaluation • Comparison to previous SotA approaches: – Chen(Zhao et al., 2009), maximum entropy – Che(Che et al., 2009), support vector machines – MatePlus(Roth and Woodsend, 2014), logistic regression and word embeddings – PathLSTM (Roth and Lapata, 2016), logistic regression for predicates and NNs with word embeddings for arguments • Additional questions: – Impact of choice of k? – Overfitting? – Impact of modeling global argument constraints? • Dataset: CoNLL-09 Shared Task data – Penn treebank w. PropBank SRL annotations – NomBank annotations not evaluated – Out-of-domain data: Brown corpus 15
  • 17. Results • Significantly outperform previous approaches – Especially on out-of-domain data • Small neighborhoods suffice • Very simple feature set – No word embeddings or verb classes 17
  • 18. Discussion • Pros: – Simple, highly transparent classification approach • Composite features make feature interactions explicit • Nearest neighborhood makes classification decision transparent – Very fast to train and test – Fast and transparent: Great for feature engineering • Cons: – IBL necessitates more feature engineering • Define composites • “Rank” composites into backoff sequences 18
  • 19. Current and Future Work • Learning instance similarity measures – Manual definition of composites, but automatic ranking – Improves quality over published numbers • Better generalization features – Word-level: Embeddings – Predicate-level: “Frame classes” • Special focus on raised arguments 19 The man broke the window. SBJ OBJ A0 The rock broke the window. SBJ OBJ A2 Creditors were told to hold off. SBJ ORPD VC IM PRT
  • 20. Current Related Work at IBM Research • Multilingual SRL – Creating “Universal Proposition Banks” on top of Universal Dependencies – Version 1.0 released: https://github.com/System- T/UniversalPropositions/ – COLING paper “Multilingual Aliasing for Auto-Generating Proposition Banks” • Poster session on Friday • Multilingual text analytics – COLING demo “Multilingual Information Extraction with PolyglotIE” • Demo session on Friday 20
  • 22. 22
  • 23. • Problem: Current SRL error-prone • Strong local bias • Many low-frequency exceptions, difficult to generalize 23 Instance-based Semantic Role Labeling • K-SRL: Instance-based learning – K-nearest neighbors • Composite features • Significantly outperform all other current systems In-domain Out-of-domain
  • 24. Instance-based Learning • Most ML algorithms – Bag of features: Syntactic function, predicate, voice … – Learn weights for features to classes • Strong weight for “passive subject” to A1 – Perform generalization • Proposed approach: Instance-based learning – kNN: k-Nearest Neighbors classification – Find the k most similar instances in training data • “all instances in which argument is a passive subject of TELL.01” • Derive class label from majority in neighborhood – No generalization – Explicitly capture local bias using composite features 24
  • 25. • Problem: Current SRL error-prone • Strong local bias, many low-frequency exceptions, difficult to generalize 25 Instance-based Semantic Role Labeling
  • 26. Composite Features and Support 26 Creditors were told to hold off. SBJ ORPD VC IM PRT TELL.01 A0: speaker (agent) A1: utterance (topic) A2: hearer (recipient) voice (V): passive predicate (P): tell path (P): VC SBJ
  • 28. 28 John hastily ordered a dozen dandelions for Mary from Amazon’s Flower Shop. order.02 (request to be delivered) A0: Orderer A1: Thing ordered A2: Benefactive, ordered-for A3: Source A0: Orderer A1: Thing ordered A2: Benefactive, ordered-for A3: SourceAM-MNR: Manner SRL: Who did what to whom, when, where and how? WHO HOW FOR WHOM DID WHAT WHERE • Problem: What type of labels are valid across languages? • Lexical, morphological and syntactic labels differ greatly • But shallow semantic labels remain stable Core idea: Predict English Semantic Role Labels for arbitrary languages Semantic Role Labeling
  • 29. The station bought Cosby reruns for record prices Buy.01A0 … spurred dollar buying by Japanese institutions. Spur.01 A1 Buy.01 A0 The company payed 2 million US$ to buy …. Corpus of annotated text dataFrame set A1 A3 Buy.01 A0 – Buyer A1 – Thing bought A2 – Seller A3 – Price paid A4 – Benefactive Pay.01 A0 – Payer A1 – Money A2 – Being payed A3 – Commodity Buy.01Pay.01A0 A1 • English SRL – FrameNet – PropBank SRL Resources

Notas do Editor

  1. Useful for : Information Extraction Question Answering (NLQ)