Word sense induction with neural BIlm and symmetric patterns

Asaf Amrami; Yoav Goldberg

Word sense induction with neural BIlm and symmetric patterns

Asaf Amrami
, Yoav Goldberg

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

45 Scopus citations

Abstract

An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We replace the ngram-based language model (LM) with a recurrent one. Beyond being more accurate, the use of the recurrent LM allows us to effectively query it in a creative way, using what we call dynamic symmetric patterns. The combination of the RNN-LM and the dynamic symmetric patterns results in strong substitute vectors for WSI, allowing to surpass the current state-of-the-art on the SemEval 2013 WSI shared task by a large margin.

Original language	English
Title of host publication	Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Editors	Ellen Riloff, David Chiang, Julia Hockenmaier, Jun'ichi Tsujii
Publisher	Association for Computational Linguistics
Pages	4860-4867
Number of pages	8
ISBN (Electronic)	9781948087841
State	Published - 1 Jan 2018
Externally published	Yes
Event	2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, Belgium Duration: 31 Oct 2018 → 4 Nov 2018

Publication series

Name	Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Conference

Conference	2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Country/Territory	Belgium
City	Brussels
Period	31/10/18 → 4/11/18

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Cite this

Amrami, A., & Goldberg, Y. (2018). Word sense induction with neural BIlm and symmetric patterns. In E. Riloff, D. Chiang, J. Hockenmaier, & J. Tsujii (Eds.), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 (pp. 4860-4867). (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018). Association for Computational Linguistics.

Amrami, Asaf ; Goldberg, Yoav. / Word sense induction with neural BIlm and symmetric patterns. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. editor / Ellen Riloff ; David Chiang ; Julia Hockenmaier ; Jun'ichi Tsujii. Association for Computational Linguistics, 2018. pp. 4860-4867 (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018).

@inproceedings{828e8647954d431aa6031c985c375fae,

title = "Word sense induction with neural BIlm and symmetric patterns",

abstract = "An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We replace the ngram-based language model (LM) with a recurrent one. Beyond being more accurate, the use of the recurrent LM allows us to effectively query it in a creative way, using what we call dynamic symmetric patterns. The combination of the RNN-LM and the dynamic symmetric patterns results in strong substitute vectors for WSI, allowing to surpass the current state-of-the-art on the SemEval 2013 WSI shared task by a large margin.",

author = "Asaf Amrami and Yoav Goldberg",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",

year = "2018",

month = jan,

day = "1",

language = "English",

series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",

publisher = "Association for Computational Linguistics",

pages = "4860--4867",

editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",

booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",

}

Amrami, A & Goldberg, Y 2018, Word sense induction with neural BIlm and symmetric patterns. in E Riloff, D Chiang, J Hockenmaier & J Tsujii (eds), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Association for Computational Linguistics, pp. 4860-4867, 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Brussels, Belgium, 31/10/18.

Word sense induction with neural BIlm and symmetric patterns. / Amrami, Asaf; Goldberg, Yoav.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. ed. / Ellen Riloff; David Chiang; Julia Hockenmaier; Jun'ichi Tsujii. Association for Computational Linguistics, 2018. p. 4860-4867 (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018).

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

TY - GEN

T1 - Word sense induction with neural BIlm and symmetric patterns

AU - Amrami, Asaf

AU - Goldberg, Yoav

PY - 2018/1/1

Y1 - 2018/1/1

N2 - An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We replace the ngram-based language model (LM) with a recurrent one. Beyond being more accurate, the use of the recurrent LM allows us to effectively query it in a creative way, using what we call dynamic symmetric patterns. The combination of the RNN-LM and the dynamic symmetric patterns results in strong substitute vectors for WSI, allowing to surpass the current state-of-the-art on the SemEval 2013 WSI shared task by a large margin.

AB - An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We replace the ngram-based language model (LM) with a recurrent one. Beyond being more accurate, the use of the recurrent LM allows us to effectively query it in a creative way, using what we call dynamic symmetric patterns. The combination of the RNN-LM and the dynamic symmetric patterns results in strong substitute vectors for WSI, allowing to surpass the current state-of-the-art on the SemEval 2013 WSI shared task by a large margin.

UR - https://www.scopus.com/pages/publications/85077509129

M3 - Conference contribution

AN - SCOPUS:85077509129

T3 - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

SP - 4860

EP - 4867

BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

A2 - Riloff, Ellen

A2 - Chiang, David

A2 - Hockenmaier, Julia

A2 - Tsujii, Jun'ichi

PB - Association for Computational Linguistics

T2 - 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Y2 - 31 October 2018 through 4 November 2018

ER -

Amrami A, Goldberg Y. Word sense induction with neural BIlm and symmetric patterns. In Riloff E, Chiang D, Hockenmaier J, Tsujii J, editors, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. Association for Computational Linguistics. 2018. p. 4860-4867. (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018).

Word sense induction with neural BIlm and symmetric patterns

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this