word representations and modelling ambiguity a case study
play

Word representations and modelling ambiguity: A case study of - PowerPoint PPT Presentation

Jul 17, 2023 •482 likes •790 views

Word representations and modelling ambiguity: A case study of metaphor Ekaterina Shutova ILLC University of Amsterdam 2 May 2018 Word representations and modelling ambiguity: A case study of metaphor 1 / 29 Polysemy and word senses The

  1. Word representations and modelling ambiguity: A case study of metaphor Ekaterina Shutova ILLC University of Amsterdam 2 May 2018 Word representations and modelling ambiguity: A case study of metaphor 1 / 29 �

  2. Polysemy and word senses The children ran to the store If you see this man, run ! Service runs all the way to Cranbury She is running a relief operation in Sudan the story or argument runs as follows Does this old car still run well? Interest rates run from 5 to 10 percent Who’s running for treasurer this year? They ran the tapes over and over again These dresses run small Word representations and modelling ambiguity: A case study of metaphor 2 / 29 �

  3. Polysemy homonymy: unrelated word senses. bank (raised land) vs bank (financial institution) bank (financial institution) vs bank (in a casino): related but distinct senses. regular polysemy and sense extension zero-derivation, e.g. tango (N) vs tango (V), or rabbit, turkey, halibut (meat / animal) metaphorical senses, e.g. swallow [food], swallow [information], swallow [anger] metonymy, e.g. he played Bach ; he drank his glass . vagueness: nurse, lecturer, driver cultural stereotypes: nurse, lecturer, driver No clearcut distinctions. Dictionaries are not consistent. Word representations and modelling ambiguity: A case study of metaphor 3 / 29 �

  4. What is metaphor? Word representations and modelling ambiguity: A case study of metaphor 4 / 29 �

  5. What is metaphor? “ A political machine ” “ The wheels of the regime were well oiled and already turning ” “ Time to mend our foreign policy ” “ 20 Steps towards a Modern, Working Democracy ” Word representations and modelling ambiguity: A case study of metaphor 5 / 29 �

  6. How does it work? Conceptual Metaphor Theory (Lakoff and Johnson, 1980) Metaphorical associations between concepts POLITICALSYSTEM is a MECHANISM � �� � � �� � source target Cross-domain knowledge projection and inference Reasoning about the target domain in terms of the properties of the source Word representations and modelling ambiguity: A case study of metaphor 6 / 29 �

  7. Computational metaphor processing tasks Learn metaphorical associations from corpora 1 “POLITICAL SYSTEM is a MECHANISM” Identify metaphorical language in text 2 “ mend the policy ” Interpret the metaphorical language 3 “ mend the policy ” means “improve the policy; address the downsides of the policy" Word representations and modelling ambiguity: A case study of metaphor 7 / 29 �

  8. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 76 watch 16 discuss 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 8 / 29 �

  9. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 76 watch 16 discuss 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 9 / 29 �

  10. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 76 watch 16 discuss 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 10 / 29 �

  11. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 76 watch 16 discuss 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 11 / 29 �

  12. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 76 watch 16 discuss 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 12 / 29 �

  13. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 76 watch 16 discuss 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 13 / 29 �

  14. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 16 discuss 76 watch 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... Word representations and modelling ambiguity: A case study of metaphor 14 / 29 �

  15. Metaphor in the distributional space N: game N: politics 1170 play 31 dominate 202 win 30 play 99 miss 28 enter 16 discuss 76 watch 66 lose 13 leave 63 start 12 understand 42 enjoy 8 study 22 finish 6 explain ... 5 shape 20 dominate 4 influence 18 quit 4 change 17 host 4 analyse 17 follow ... 17 control 2 transform ... ... NEED TO FIND A WAY TO PARTITION THE SPACE Word representations and modelling ambiguity: A case study of metaphor 15 / 29 �

  16. Learning metaphorical associations by soft clustering Unsupervised Metaphor Identification Using Hierarchical Graph Factorization Clustering . Shutova and Sun, 2013. NAACL. ... Word representations and modelling ambiguity: A case study of metaphor 16 / 29 �

  17. Learning metaphorical associations by soft clustering GAME DEMOCRACY ENGINE SPORT AUTOCRACY MACHINE … ... ... play compete function ... break repair ... DEMOCRACY AUTOCRACY MACHINE ENGINE GAME SPORT ... ... ... Word representations and modelling ambiguity: A case study of metaphor 17 / 29 �

  18. Creating the graph Experimental setup v 1 v 2 u 1 ALGORITHM : Hierarchical graph v 3 factorization clustering (Yu, Yu, Tresp, 2006) q 1 v 4 u 2 v 5 DATASET : 2000 frequent nouns v 6 FEATURES : verbs in subject, direct and v 7 q 2 indirect object relations (Gigaword corpus) u 3 v 8 v 9 LEVELS : 10 Word representations and modelling ambiguity: A case study of metaphor 18 / 29 �

  19. Hierarchical clustering using graph factorization v 2 v 1 v 3 v 7 v 8 v 9 v 6 v 5 v 4 Similarity matrix W : w ij = JSD ( v i , v j ) Word representations and modelling ambiguity: A case study of metaphor 19 / 29 �

  20. Hierarchical clustering using graph factorization v 1 v 2 u 1 v 2 v 1 v 3 v 3 v 7 v 4 v 8 v 5 u 2 v 9 v 6 v 6 v 5 v 7 v 4 u 3 v 8 v 9 Similarity matrix W : w ij = JSD ( v i , v j ) Word representations and modelling ambiguity: A case study of metaphor 20 / 29 �

  21. Hierarchical clustering using graph factorization v 1 v 2 u 1 v 2 v 1 v 3 v 3 v 7 v 4 v 8 u 2 v 5 v 9 v 6 v 6 v 5 v 7 v 4 u 3 v 8 v 9 b ip b jp ij = � m W ′ : w ′ Similarity matrix W : p = 1 λ p w ij = JSD ( v i , v j ) b ip – connection weight λ i = � n i = 1 b ip Word representations and modelling ambiguity: A case study of metaphor 21 / 29 �

  22. Hierarchical clustering using graph factorization v 1 u 1 v 2 u 1 v 2 v 1 v 2 v 1 v 3 v 3 v 7 v 3 v 7 v 4 v 8 v 8 u 2 v 9 v 5 v 9 u 2 v 6 v 6 v 6 v 5 v 5 v 7 v 4 u 3 v 4 u 3 v 8 v 9 b ip b jp ij = � m W ′ : w ′ Similarity matrix W : p = 1 λ p w ij = JSD ( v i , v j ) b ip – connection weight λ i = � n i = 1 b ip Word representations and modelling ambiguity: A case study of metaphor 22 / 29 �

  23. Hierarchical clustering using graph factorization v 1 u 1 v 2 u 1 v 2 v 1 v 2 v 1 v 3 u 1 u 2 v 3 v 7 v 3 v 7 v 4 v 8 v 8 u 2 v 9 v 5 v 9 u 2 v 6 v 6 v 6 u 3 v 5 v 5 v 7 v 4 u 3 v 4 u 3 v 8 v 9 b ip b jp ij = � m W ′ : w ′ Similarity matrix W : p = 1 λ p w ij = JSD ( v i , v j ) b ip – connection weight λ i = � n i = 1 b ip Word representations and modelling ambiguity: A case study of metaphor 23 / 29 �

  24. Hierarchical clustering using graph factorization v 1 v 1 u 1 v 2 v 2 u 1 v 2 v 1 u 1 v 2 v 1 v 3 v 3 u 1 u 2 v 3 v 7 q 1 v 3 v 7 v 4 v 4 v 8 v 8 u 2 v 9 u 2 v 5 v 5 v 9 u 2 v 6 v 6 v 6 v 6 u 3 v 5 v 5 v 7 v 4 v 7 u 3 v 4 q 2 u 3 u 3 v 8 v 8 v 9 v 9 b ip b jp ij = � m W ′ : w ′ Similarity matrix W : p = 1 λ p w ij = JSD ( v i , v j ) b ip – connection weight λ i = � n i = 1 b ip Word representations and modelling ambiguity: A case study of metaphor 24 / 29 �

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Language Modelling Makes Sense Propagating Representations through WordNet for Full-Coverage Word

Language Modelling Makes Sense Propagating Representations through WordNet for Full-Coverage Word

Language Modelling Makes Sense Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation Da Daniel l Lo Loureiro, Alpio Jorge ACL Florence, 31 July 2019 Sense Embeddings Exploiting the latest Neural

1.16k views • 66 slides
NLU lecture 5: Word representations and morphology Adam Lopez alopez@inf.ed.ac.uk Essential

NLU lecture 5: Word representations and morphology Adam Lopez alopez@inf.ed.ac.uk Essential

NLU lecture 5: Word representations and morphology Adam Lopez alopez@inf.ed.ac.uk Essential epistemology Word representations and word2vec Word representations and compositional morphology Reading: Mikolov et al. 2013, Luong et al.

746 views • 42 slides
Incorporating Relational Knowledge into Word Representations using Subspace Regularization Jun

Incorporating Relational Knowledge into Word Representations using Subspace Regularization Jun

Incorporating Relational Knowledge into Word Representations using Subspace Regularization Jun Araki (Carnegie Mellon University) joint work with Abhishek Kumar (IBM Research) ACL 2016 Distributed word representations Low-dimensional dense

378 views • 18 slides
Inside Out: Two Jointly Predictive Models for Word Representations and Phrase Representations Fei

Inside Out: Two Jointly Predictive Models for Word Representations and Phrase Representations Fei

Inside Out: Two Jointly Predictive Models for Word Representations and Phrase Representations Fei Sun , Jiafeng Guo, Yanyan Lan, Jun Xu, and Xueqi Cheng ofey.sunfei@gmail.com CAS Key Lab of Network Data Science and Technology Institute of

701 views • 37 slides
Distributed word representations Christopher Potts CS 244U: Natural language understanding April

Distributed word representations Christopher Potts CS 244U: Natural language understanding April

Overview Entailment in vector space Shallow neural nets Lexical ambiguity Conclusion Refs. Distributed word representations Christopher Potts CS 244U: Natural language understanding April 9 1 / 44 Overview Entailment in vector space

903 views • 64 slides
09-00 - 09.10 Word of welcome & General introduction 09.10 - 09.50 Interactive case study

09-00 - 09.10 Word of welcome & General introduction 09.10 - 09.50 Interactive case study

09-00 - 09.10 Word of welcome & General introduction 09.10 - 09.50 Interactive case study working groups, including video introductions Ethiopia: Water scarcity and source protection. The Philippines: Resilience and disaster preparedness.

481 views • 11 slides
Case Study: Modelling using Objects Murray Cole Classes & Objects 1 Modelling the

Case Study: Modelling using Objects Murray Cole Classes & Objects 1 Modelling the

I V N E U R S E I H T Y T O H F G R E U D I B N Case Study: Modelling using Objects Murray Cole Classes & Objects 1 Modelling the world with data Specifying systems is one of the hardest tasks in SE Key

195 views • 15 slides
The Cooperative Cleaners Case Study: Modelling and Analysis in Real-Time ABS Silvia Lizeth Tapia

The Cooperative Cleaners Case Study: Modelling and Analysis in Real-Time ABS Silvia Lizeth Tapia

Motivation The Cooperative Cleaners Case Study Results Conclusions Future Work The Cooperative Cleaners Case Study: Modelling and Analysis in Real-Time ABS Silvia Lizeth Tapia Tarifa Precise Modelling and Analysis University of Oslo

469 views • 27 slides
Word Meaning: Distributional Representations & Word Sense Disambiguation CMSC 723 / LING 723

Word Meaning: Distributional Representations & Word Sense Disambiguation CMSC 723 / LING 723

Word Meaning: Distributional Representations & Word Sense Disambiguation CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides credit: Dan Jurafsky Reminders Read the syllabus Make sure you have access to piazza Get started on

691 views • 54 slides
Ambiguity and the Lexicon in Natural Language Informatics 2A: Lecture 12 2 The Lexicon Word

Ambiguity and the Lexicon in Natural Language Informatics 2A: Lecture 12 2 The Lexicon Word

Ambiguity in Language Ambiguity in Language The Lexicon The Lexicon 1 Ambiguity in Language Derivations and Structural Ambiguity Dealing with Ambiguity Ambiguity and the Lexicon in Natural Language Informatics 2A: Lecture 12 2 The Lexicon

100 views • 6 slides
Ambiguity Resolved PPP A Case Study in NSW Thomas Grinter, Volker Janssen, Craig Roberts

Ambiguity Resolved PPP A Case Study in NSW Thomas Grinter, Volker Janssen, Craig Roberts

Ambiguity Resolved PPP A Case Study in NSW Thomas Grinter, Volker Janssen, Craig Roberts How it works GNSS Constellation IGS CORS Network GNSS Satellite Orbits GNSS User PPP Network Process (Satellite Clock Estimates + Additional

366 views • 13 slides
Alternative Representations. A Case Study of Proportional Judgements Jakub Szymanik Shane

Alternative Representations. A Case Study of Proportional Judgements Jakub Szymanik Shane

Alternative Representations. A Case Study of Proportional Judgements Jakub Szymanik Shane Steinert-Threlkeld Gert-Jan Munneke Institute for Logic, Language and Computation University of Amsterdam LCQ15 Outline Introduction

643 views • 39 slides
Tariff case study Modelling the effect of cost-reflec7ve

Tariff case study Modelling the effect of cost-reflec7ve

Tariff case study Modelling the effect of cost-reflec7ve electricity network tariffs on consumers using real customer data (Interim results) Melissa James

1.85k views • 29 slides
Statechart modelling of NPC behaviour Kevin Wyckmans Overview Introduction Case study: Tank

Statechart modelling of NPC behaviour Kevin Wyckmans Overview Introduction Case study: Tank

Statechart modelling of NPC behaviour Kevin Wyckmans Overview Introduction Case study: Tank Wars Modelling Game AI Time Code generation Agent based spreading of diseases 2/25 Introduction As the realism in games increases, so does the

688 views • 25 slides
Sentence and Contextualised Word Representations Graham Neubig Site

Sentence and Contextualised Word Representations Graham Neubig Site

CS11-747 Neural Networks for NLP Sentence and Contextualised Word Representations Graham Neubig Site https://phontron.com/class/nn4nlp2019/ (w/ slides by Antonis Anastasopoulos) Sentence Representations We can create a vector or sequence

619 views • 43 slides
Using Machine Learning to Study the Neural Representations of Language Meanings Tom M. Mitchell

Using Machine Learning to Study the Neural Representations of Language Meanings Tom M. Mitchell

Using Machine Learning to Study the Neural Representations of Language Meanings Tom M. Mitchell Carnegie Mellon University June 2017 How does neural activity encode word meanings? How does neural activity encode word meanings? How does

673 views • 64 slides
Secure Communications over the Internet Part 2 Hassen Sallay, Ph.D WHY USE THE INTERNET for

Secure Communications over the Internet Part 2 Hassen Sallay, Ph.D WHY USE THE INTERNET for

Secure Communications over the Internet Part 2 Hassen Sallay, Ph.D WHY USE THE INTERNET for Secure Communications? The Internet offers: Virtually universal worldwide coverage. Access to anywhere from anywhere, stationary or mobile.

788 views • 47 slides
Topics in Computational Sustainability CS 325 Spring 2016 Lecture 1: Intro Course information

Topics in Computational Sustainability CS 325 Spring 2016 Lecture 1: Intro Course information

Topics in Computational Sustainability CS 325 Spring 2016 Lecture 1: Intro Course information (Administrivia) Examples of Computational Sustainability Projects Spring 2016 Course Information Lectures : Tuesdays and Thursdays - 10:30 11:50

1.04k views • 31 slides
"How can we make them get it?" Findings from research on communicating ocean sciences

"How can we make them get it?" Findings from research on communicating ocean sciences

"How can we make them get it?" Findings from research on communicating ocean sciences to public audiences. CSULB, STARS Seminar, 10/26/09 Shawn Rowe Oregon Sea Grant Extension Learning Specialist Assistant Professor, Science and

495 views • 33 slides
Lecture 2.2: Initial value problems Matthew Macauley Department of Mathematical Sciences Clemson

Lecture 2.2: Initial value problems Matthew Macauley Department of Mathematical Sciences Clemson

Lecture 2.2: Initial value problems Matthew Macauley Department of Mathematical Sciences Clemson University http://www.math.clemson.edu/~macaule/ Math 2080, Differential Equations M. Macauley (Clemson) Lecture 2.2: Initial value problems

267 views • 10 slides
Model Selection in Survival Analysis Suppose we have a censored survival time that we want to

Model Selection in Survival Analysis Suppose we have a censored survival time that we want to

Model Selection in Survival Analysis Suppose we have a censored survival time that we want to model as a function of a (possibly ) set of covariates. Two important questions are: How to decide which covariates to use How to decide if the

640 views • 39 slides
6702 Topics in Computa2onal Sustainability Spring 2011

6702 Topics in Computa2onal Sustainability Spring 2011

6702 Topics in Computa2onal Sustainability Spring 2011 Administra2ve Organiza2on 6702 Overview Computa2onal Sustainability 6702 topics Examples of

572 views • 43 slides
Optimal Harvesting with Coupled Population and Price Dynamics Floyd B. Hanson Laboratory for

Optimal Harvesting with Coupled Population and Price Dynamics Floyd B. Hanson Laboratory for

Optimal Harvesting with Coupled Population and Price Dynamics Floyd B. Hanson Laboratory for Advanced Computing University of Illinois at Chicago and Dennis Ryan Division of Science and Mathematics McKendree College SIAM 50th Anniversary

348 views • 31 slides
Computer Vision 16-385 Lecturer: Kris Kitani TAs: Prakruti Gogia, Animesh Ramesh, Abhinav

Computer Vision 16-385 Lecturer: Kris Kitani TAs: Prakruti Gogia, Animesh Ramesh, Abhinav

Spring 2017 Carnegie Mellon University Computer Vision 16-385 Lecturer: Kris Kitani TAs: Prakruti Gogia, Animesh Ramesh, Abhinav Garlapati, Shaurya Shankar, Chen Kong Class: MW 1:30 to 2:50 Room: DH 1212 today staff

490 views • 23 slides

More recommend