heterogeneous lexical resources
play

Heterogeneous Lexical Resources MultiJEDI ERC 259234 Lexical - PowerPoint PPT Presentation

Mar 30, 2023 •525 likes •1.18k views

A Robust Approach to Aligning Heterogeneous Lexical Resources MultiJEDI ERC 259234 Lexical Resource Lexical Resource Lexical Resource Why combine resources? e.g., named entities, new senses dozens of new languages

  1. A Robust Approach to Aligning Heterogeneous Lexical Resources MultiJEDI ERC 259234

  2. Lexical Resource

  3. Lexical Resource

  4. Lexical Resource

  5. Why combine resources?   e.g., named entities, new senses    dozens of new languages   e.g., Hypernymy, meronymy, etc.

  6. Why combine resources?

  7. Difficulty of resource alignment

  8. How resource alignment works? •

  9. How resource alignment works? • •

  10. How resource alignment works?

  11. Denfinitional similarity

  12. Denfinitional similarity • • • • plant -- Buildings for carrying on industrial labor. plant -- The necessary infrastructure used in support and maintenance of a given facility.

  13. Contributions

  14. Our approach: SemAlign

  15. Our approach: SemAlign

  16. Our approach: SemAlign

  17. SemAlign: structural similarity

  18. SemAlign: core

  19. Semantic Signature of a concept Personalized PageRank

  20. Semantic Signature of a concept Personalized PageRank

  21. SemAlign

  22. SemAlign

  23. SemAlign: signature unification

  24. SemAlign: signature unification

  25. SemAlign: signature unification

  26. SemAlign: signature unification

  27. Semantic Signature Comparison

  28. Semantic Signature Comparison Weighted Overlap (Pilehvar et al., ACL 2013)

  29. SemAlign: score combination

  30. Ontologization of lexical resources

  31. Ontologization of lexical resources

  32. Ontologization of lexical resources

  33. Ontologization of lexical resources

  34. Ontologization of lexical resources

  35. Ontologization of lexical resources

  36. Ontologization of lexical resources

  37. Ontologization of lexical resources

  38. Ontologization of lexical resources

  39. Ontologization of lexical resources

  40. Ontologization of lexical resources

  41. Ontologization of lexical resources

  42. Ontologization of lexical resources

  43. Ontologization of lexical resources

  44. Ontologization of lexical resources

  45. Ontologization : similarity-based disambiguation

  46. Ontologization : similarity-based disambiguation

  47. Ontologization : similarity-based disambiguation

  48. Ontologization : similarity-based disambiguation

  49. Ontologization : similarity-based disambiguation

  50. Ontologization: evaluation

  51. Alignment Experiments: Datasets (Matuschek & Gurevych, TACL 2013)

  52. Alignment Experiments: System configurations 𝜸 𝜸 𝜸

  53. Alignment Experiments: System configurations 𝜾

  54. Alignment Experiments: System configurations 𝜸 𝜾

  55. Alignment Experiments: System configurations 𝜸 𝜾

  56. Alignment Experiments: System configurations 𝜸 𝜾

  57. Comparison system

  58. Alignment Experiments

  59. Alignment Experiments

  60. SemAlign: structural similarity

  61. Alignment Experiments

  62. Conclusions • – – • • –

  63. Future directions • • •

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

Unifying Heterogeneous Cray Unifying Heterogeneous Cray Resources and Systems into an

Unifying Heterogeneous Cray Unifying Heterogeneous Cray Resources and Systems into an

Unifying Heterogeneous Cray Unifying Heterogeneous Cray Resources and Systems into an Intelligent Single-scheduled Environment Scott Jackson Engineering Confidential and Proprietary Overview Introduction Heterogeneous Resources

690 views • 34 slides
Lexical sense alignment using weighted bipartite b -matching Sina Ahmadi (ULD) Supervisors: John

Lexical sense alignment using weighted bipartite b -matching Sina Ahmadi (ULD) Supervisors: John

Lexical sense alignment using weighted bipartite b -matching Sina Ahmadi (ULD) Supervisors: John McCrae, Mihael Arcan 16th Ph.D. day on April 8, 2018 Lexical resources 2 Lexical resources Expert-made Collaboratively-curated 3 Why

524 views • 19 slides
VerbNet: extensions and mappings to other lexical resources Karin Kipper Schuler

VerbNet: extensions and mappings to other lexical resources Karin Kipper Schuler

VerbNet: extensions and mappings to other lexical resources Karin Kipper Schuler kipper@linc.cis.upenn.edu June 26th, 2006 Overview Real world applications need resources with rich syntactic and se- mantic representations. Many existing

612 views • 40 slides
Lexical Databases Like a dictionary Lexical properties of interest to psycholinguists

Lexical Databases Like a dictionary Lexical properties of interest to psycholinguists

A General Introduction to Lexical Databases Emmanuel Keuleers Department of Experimental Psychology Ghent University EMLAR 2015 - Utrecht, April 15-17, 2015 What can you find in a lexical database? How can you find it? Lexical

905 views • 45 slides
Induction of Treebank-Aligned Lexical Resources LREC 2008 Tejaswini Deoskar, Mats Rooth

Induction of Treebank-Aligned Lexical Resources LREC 2008 Tejaswini Deoskar, Mats Rooth

Induction of Treebank-Aligned Lexical Resources LREC 2008 Tejaswini Deoskar, Mats Rooth Department of Linguistics Cornell University Induction of Treebank-Aligned Lexical Resources p. 1/2 Overview Goal: Induction of probabilistic

672 views • 54 slides
From Dictionaries to Cross-lingual Lexical Resources Guadalupe Aguado-de-Cea, Elena

From Dictionaries to Cross-lingual Lexical Resources Guadalupe Aguado-de-Cea, Elena

From Dictionaries to Cross-lingual Lexical Resources Guadalupe Aguado-de-Cea, Elena Montiel-Ponsoda, Ilan Kernerman, Noam Ordan Ontology Engineering Group (OEG) Universidad Politcnica de Madrid (UPM) {lupe,emontiel}@fi.upm.es K

392 views • 21 slides
Introduction to Lexical Analysis Outline Informal sketch of lexical analysis

Introduction to Lexical Analysis Outline Informal sketch of lexical analysis

Introduction to Lexical Analysis Outline Informal sketch of lexical analysis Identifies tokens in input string Issues in lexical analysis Lookahead Ambiguities Specifying lexical analyzers (lexers) Regular

699 views • 49 slides
Lexical Knowledge Structures By Ashutosh Kumar Nirala (10305906) MTech-II, CSE Guide - Dr.

Lexical Knowledge Structures By Ashutosh Kumar Nirala (10305906) MTech-II, CSE Guide - Dr.

Lexical Knowledge Structures By Ashutosh Kumar Nirala (10305906) MTech-II, CSE Guide - Dr. Pushpak Bhattacharyya IIT Bombay July 10, 2012 A K Nirala Lexical Knowledge Structures Overview Need of Lexical resources. Making computers

1.72k views • 104 slides
The Effects of Institutions and Natural Resources in Heterogeneous Growth Regimes Yacine BELARBI 1

The Effects of Institutions and Natural Resources in Heterogeneous Growth Regimes Yacine BELARBI 1

The Effects of Institutions and Natural Resources in Heterogeneous Growth Regimes Yacine BELARBI 1 Sad SOUAM 2 Lylia SAMI 3 Abstract For more than a decade, the dependence to natural resources is the object of a wide debate in the analysis of

506 views • 16 slides
Lexical analysis Lexical analysis Lexical analysis checks the correctness of program words and

Lexical analysis Lexical analysis Lexical analysis checks the correctness of program words and

Lexical analysis Lexical analysis Lexical analysis checks the correctness of program words and transforms a program to the stream of tokens: removes empty symbols and commentaries; identifies keywords, indentifiers and literal

400 views • 37 slides
Inducing Interpretable Word Senses for WSD and Enrichment of Lexical Resources Overview Jan 11,

Inducing Interpretable Word Senses for WSD and Enrichment of Lexical Resources Overview Jan 11,

Alexander Panchenko Inducing Interpretable Word Senses for WSD and Enrichment of Lexical Resources Overview Jan 11, 2018 Inducing Interpretable Word Senses for WSD and Enrichment of Lexical Resources, Alexander Panchenko 2/54 Making induced

877 views • 69 slides
Lexical Resources in GF Krasimir Angelov University of Gothenburg July 15, 2015 History 1

Lexical Resources in GF Krasimir Angelov University of Gothenburg July 15, 2015 History 1

Lexical Resources in GF Krasimir Angelov University of Gothenburg July 15, 2015 History 1 English 2 Translations 3 GF Lexicon vs WordNet 4 Some History 2008 OALD imported (Bj orn Bringert) 2010 Further development for wide coverage

414 views • 17 slides
Lexical Semantics Martin Rajman & Jean-Cdric Chappelier Overview Basic concepts

Lexical Semantics Martin Rajman & Jean-Cdric Chappelier Overview Basic concepts

Lexical Semantics Martin Rajman & Jean-Cdric Chappelier Overview Basic concepts Semantic relations Resources for Lexical Semantics: Wordnet Applications of Lexical Semantics Word Sense Disambiguation Basic concepts

1.09k views • 60 slides
ACCESSING TEXT CORPORA AND LEXICAL RESOURCES Accessing Text Corpora Conditional Frequency

ACCESSING TEXT CORPORA AND LEXICAL RESOURCES Accessing Text Corpora Conditional Frequency

CS372 Spring 2013 2013-03-12 Natural Language Processing with Python CS372: Spring, 20 13 Lecture 3 Jong C. Park Department of Computer Science Korea Advanced Institute of Science and Technology ACCESSING TEXT CORPORA AND LEXICAL RESOURCES

237 views • 19 slides
Introduction to Lexical Analysis Outline Informal sketch of lexical analysis

Introduction to Lexical Analysis Outline Informal sketch of lexical analysis

Introduction to Lexical Analysis Outline Informal sketch of lexical analysis Identifies tokens in input string Issues in lexical analysis Lookahead Ambiguities Specifying lexers Regular expressions

724 views • 34 slides
LEXICAL SEMANTICS LEXICAL SEMANTICS CS 224N 2011 Gerald Penn Slides largely adapted from

LEXICAL SEMANTICS LEXICAL SEMANTICS CS 224N 2011 Gerald Penn Slides largely adapted from

LEXICAL SEMANTICS LEXICAL SEMANTICS CS 224N 2011 Gerald Penn Slides largely adapted from ones by Christopher Manning, Massimo Poesio, Ted Pedersen, Dan Jurafsky, and Jim Martin 1 Lexical information and NL applications Lexical

732 views • 72 slides
SCALEDEEP Bryce Paputa and Royce Hwang Motivation: DNN Applications Google image search,

SCALEDEEP Bryce Paputa and Royce Hwang Motivation: DNN Applications Google image search,

SCALEDEEP Bryce Paputa and Royce Hwang Motivation: DNN Applications Google image search, Apple Siri Self-driving cars, Education, Healthcare Source: https://deepmind.com/ Source:

541 views • 29 slides
Oregon NFIP Biological Opinion Implementation Planning Partner Webinar March 20, 2020 WELCOME!

Oregon NFIP Biological Opinion Implementation Planning Partner Webinar March 20, 2020 WELCOME!

Oregon NFIP Biological Opinion Implementation Planning Partner Webinar March 20, 2020 WELCOME! Erin Cooper , CFM Bonnie Shorin NFIP-ESA Specialist NOAA Fisheries FEMA Region 10 bonnie.shorin@noaa.gov Erin.cooper@fema.dhs.gov Celinda

831 views • 46 slides
Thank you for joining us! All phone lines are muted; please type in your questions into the

Thank you for joining us! All phone lines are muted; please type in your questions into the

Thank you for joining us! All phone lines are muted; please type in your questions into the Questions box in the webinar controls on the right side of your screen. Well answer questions during several questions breaks in the

615 views • 35 slides
Introduction Mitchell, Chapter 1 CptS 570 Machine Learning School of EECS Washington State

Introduction Mitchell, Chapter 1 CptS 570 Machine Learning School of EECS Washington State

Introduction Mitchell, Chapter 1 CptS 570 Machine Learning School of EECS Washington State University Outline Why machine learning Some examples Relevant disciplines What is a well-defined learning problem Learning to play

520 views • 20 slides
sequencing data https://github.com/DRL/blobtools thanks to Sujai Kumar, Dominik Laetsch (Blaxter

sequencing data https://github.com/DRL/blobtools thanks to Sujai Kumar, Dominik Laetsch (Blaxter

Blobtools: exploring contamination in raw sequencing data https://github.com/DRL/blobtools thanks to Sujai Kumar, Dominik Laetsch (Blaxter lab - Universiy of Edinburgh) Toni Beltran BLM, 15 th March Genome assembly is an attempt to accurately

350 views • 21 slides
KamLAND Koji Ishidoshiro (Tohoku University) for KamLAND collaboration The 14th International

KamLAND Koji Ishidoshiro (Tohoku University) for KamLAND collaboration The 14th International

KamLAND Koji Ishidoshiro (Tohoku University) for KamLAND collaboration The 14th International Workshop on Next generation Nucleon Decay and Neutrino Detectors KamLAND collaboration University of Hida, Japan 46 scientists 11 institutes,

754 views • 58 slides
The Planet-Metallicity Correlation for Hot Jupiters Daniel Bayliss University of Geneva The

The Planet-Metallicity Correlation for Hot Jupiters Daniel Bayliss University of Geneva The

The Planet-Metallicity Correlation for Hot Jupiters Daniel Bayliss University of Geneva The National Centres of Competence in Research (NCCR) [ESA/C. Carreau] are a research instrument of the Swiss National Science Foundation Background

528 views • 17 slides
How to form asteroids from mm-sized grains D. Carrera 1 , A. Johansen 1 , M. B. Davies 1 Talk

How to form asteroids from mm-sized grains D. Carrera 1 , A. Johansen 1 , M. B. Davies 1 Talk

Twenty years of giant exoplanets - Proceedings of the Haute Provence Observatory Colloquium, 5-9 October 2015 Edited by I. Boisse, O. Demangeon, F. Bouchy & L. Arnold How to form asteroids from mm-sized grains D. Carrera 1 , A. Johansen 1 , M.

292 views • 4 slides

More recommend