Learning to identify the best contexts for knowledge-based WSD

Evgenia Wasserman-Pritsker; William W. Cohen; Einat Minkov

doi:10.18653/v1/d15-1192

Learning to identify the best contexts for knowledge-based WSD

Evgenia Wasserman-Pritsker, William W. Cohen, Einat Minkov

Department of Information Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We outline a learning framework that aims at identifying useful contextual cues for knowledge-based word sense disambiguation. The usefulness of individual context words is evaluated based on diverse lexico-statistical and syntactic information, as well as simple word distance. Experiments using two different knowledge-based methods and benchmark datasets show significant improvements due to context modeling, beating the conventional window-based approach.

Original language	English
Title of host publication	Conference Proceedings - EMNLP 2015
Subtitle of host publication	Conference on Empirical Methods in Natural Language Processing
Publisher	Association for Computational Linguistics (ACL)
Pages	1662-1667
Number of pages	6
ISBN (Electronic)	9781941643327
DOIs	https://doi.org/10.18653/v1/d15-1192
State	Published - 2015
Event	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal Duration: 17 Sep 2015 → 21 Sep 2015

Publication series

Name	Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

Conference

Conference	Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → 21/09/15

Bibliographical note

Publisher Copyright:
© 2015 Association for Computational Linguistics.

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Access to Document

10.18653/v1/d15-1192

Cite this

Wasserman-Pritsker, E., Cohen, W. W., & Minkov, E. (2015). Learning to identify the best contexts for knowledge-based WSD. In Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing (pp. 1662-1667). (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d15-1192

Wasserman-Pritsker, Evgenia ; Cohen, William W. ; Minkov, Einat. / Learning to identify the best contexts for knowledge-based WSD. Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2015. pp. 1662-1667 (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing).

@inproceedings{668ef7bcef5f4573a4d5f3ba1d79b0dc,

title = "Learning to identify the best contexts for knowledge-based WSD",

abstract = "We outline a learning framework that aims at identifying useful contextual cues for knowledge-based word sense disambiguation. The usefulness of individual context words is evaluated based on diverse lexico-statistical and syntactic information, as well as simple word distance. Experiments using two different knowledge-based methods and benchmark datasets show significant improvements due to context modeling, beating the conventional window-based approach.",

author = "Evgenia Wasserman-Pritsker and Cohen, {William W.} and Einat Minkov",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 ; Conference date: 17-09-2015 Through 21-09-2015",

year = "2015",

doi = "10.18653/v1/d15-1192",

language = "English",

series = "Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1662--1667",

booktitle = "Conference Proceedings - EMNLP 2015",

address = "United States",

}

Wasserman-Pritsker, E, Cohen, WW & Minkov, E 2015, Learning to identify the best contexts for knowledge-based WSD. in Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics (ACL), pp. 1662-1667, Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 17/09/15. https://doi.org/10.18653/v1/d15-1192

Learning to identify the best contexts for knowledge-based WSD. / Wasserman-Pritsker, Evgenia; Cohen, William W.; Minkov, Einat.

Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), 2015. p. 1662-1667 (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning to identify the best contexts for knowledge-based WSD

AU - Wasserman-Pritsker, Evgenia

AU - Cohen, William W.

AU - Minkov, Einat

PY - 2015

Y1 - 2015

N2 - We outline a learning framework that aims at identifying useful contextual cues for knowledge-based word sense disambiguation. The usefulness of individual context words is evaluated based on diverse lexico-statistical and syntactic information, as well as simple word distance. Experiments using two different knowledge-based methods and benchmark datasets show significant improvements due to context modeling, beating the conventional window-based approach.

AB - We outline a learning framework that aims at identifying useful contextual cues for knowledge-based word sense disambiguation. The usefulness of individual context words is evaluated based on diverse lexico-statistical and syntactic information, as well as simple word distance. Experiments using two different knowledge-based methods and benchmark datasets show significant improvements due to context modeling, beating the conventional window-based approach.

UR - http://www.scopus.com/inward/record.url?scp=84959913648&partnerID=8YFLogxK

U2 - 10.18653/v1/d15-1192

DO - 10.18653/v1/d15-1192

M3 - Conference contribution

AN - SCOPUS:84959913648

T3 - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

SP - 1662

EP - 1667

BT - Conference Proceedings - EMNLP 2015

PB - Association for Computational Linguistics (ACL)

T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015

Y2 - 17 September 2015 through 21 September 2015

ER -

Wasserman-Pritsker E, Cohen WW, Minkov E. Learning to identify the best contexts for knowledge-based WSD. In Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL). 2015. p. 1662-1667. (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing). doi: 10.18653/v1/d15-1192

Learning to identify the best contexts for knowledge-based WSD

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this