Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity

John Harvill; Roxana Girju; Mark Hasegawa-Johnson

doi:10.18653/v1/2022.naacl-main.386

Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity

John Harvill, Roxana Girju, Mark Hasegawa-Johnson

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

Abstract

In this paper we focus on patterns of colexification (co-expressions of form-meaning mapping in the lexicon) as an aspect of lexical-semantic organization, and use them to build large scale synset graphs across BabelNet's typologically diverse set of 499 world languages. We introduce and compare several approaches: monolingual and cross-lingual colexification graphs, popular distributional models, and fusion approaches. The models are evaluated against human judgments on a semantic similarity task for nine languages. Our strong empirical findings also point to the importance of universality of our graph synset embedding representations with no need for any language-specific adaptation when evaluated on the lexical similarity task. The insights of our exploratory investigation of large-scale colexification graphs could inspire significant advances in NLP across languages, especially for tasks involving languages which lack dedicated lexical resources, and can benefit from language transfer from large shared cross-lingual semantic spaces.

Original language	English (US)
Title of host publication	Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies
Editors	Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Publisher	Association for Computational Linguistics
Pages	5259-5270
Number of pages	11
ISBN (Electronic)	9781955917711
DOIs	https://doi.org/10.18653/v1/2022.naacl-main.386
State	Published - Jul 2022
Event	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - Seattle, United States Duration: Jul 10 2022 → Jul 15 2022

Conference

Conference	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022
Country/Territory	United States
City	Seattle
Period	7/10/22 → 7/15/22

Keywords

linguistic typology, senses, synsets, semantics, knowledge transfer, cross-lingual, semantic similarity

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Information Systems
Software

Online availability

10.18653/v1/2022.naacl-main.386License: CC BY

Library availability

Discover UIUC Full Text

Cite this

Harvill, J., Girju, R., & Hasegawa-Johnson, M. (2022). Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity. In M. Carpuat, M.-C. de Marneffe, & I. V. Meza Ruiz (Eds.), Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 5259-5270). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.naacl-main.386

Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity. / Harvill, John; Girju, Roxana; Hasegawa-Johnson, Mark.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ed. / Marine Carpuat; Marie-Catherine de Marneffe; Ivan Vladimir Meza Ruiz. Association for Computational Linguistics, 2022. p. 5259-5270.

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

Harvill, J, Girju, R & Hasegawa-Johnson, M 2022, Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity. in M Carpuat, M-C de Marneffe & IV Meza Ruiz (eds), Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, pp. 5259-5270, 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, United States, 7/10/22. https://doi.org/10.18653/v1/2022.naacl-main.386

Harvill J, Girju R, Hasegawa-Johnson M. Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity. In Carpuat M, de Marneffe MC, Meza Ruiz IV, editors, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics. 2022. p. 5259-5270 doi: 10.18653/v1/2022.naacl-main.386

Harvill, John ; Girju, Roxana ; Hasegawa-Johnson, Mark. / Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. editor / Marine Carpuat ; Marie-Catherine de Marneffe ; Ivan Vladimir Meza Ruiz. Association for Computational Linguistics, 2022. pp. 5259-5270

@inproceedings{9f4280e83ba344c5b1cd9b9a17a780a8,

title = "Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity",

abstract = "In this paper we focus on patterns of colexification (co-expressions of form-meaning mapping in the lexicon) as an aspect of lexical-semantic organization, and use them to build large scale synset graphs across BabelNet's typologically diverse set of 499 world languages. We introduce and compare several approaches: monolingual and cross-lingual colexification graphs, popular distributional models, and fusion approaches. The models are evaluated against human judgments on a semantic similarity task for nine languages. Our strong empirical findings also point to the importance of universality of our graph synset embedding representations with no need for any language-specific adaptation when evaluated on the lexical similarity task. The insights of our exploratory investigation of large-scale colexification graphs could inspire significant advances in NLP across languages, especially for tasks involving languages which lack dedicated lexical resources, and can benefit from language transfer from large shared cross-lingual semantic spaces.",

keywords = "linguistic typology, senses, synsets, semantics, knowledge transfer, cross-lingual, semantic similarity",

author = "John Harvill and Roxana Girju and Mark Hasegawa-Johnson",

year = "2022",

month = jul,

doi = "10.18653/v1/2022.naacl-main.386",

language = "English (US)",

pages = "5259--5270",

editor = "Marine Carpuat and {de Marneffe}, Marie-Catherine and {Meza Ruiz}, {Ivan Vladimir}",

booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 ; Conference date: 10-07-2022 Through 15-07-2022",

}

TY - GEN

T1 - Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity

AU - Harvill, John

AU - Girju, Roxana

AU - Hasegawa-Johnson, Mark

PY - 2022/7

Y1 - 2022/7

N2 - In this paper we focus on patterns of colexification (co-expressions of form-meaning mapping in the lexicon) as an aspect of lexical-semantic organization, and use them to build large scale synset graphs across BabelNet's typologically diverse set of 499 world languages. We introduce and compare several approaches: monolingual and cross-lingual colexification graphs, popular distributional models, and fusion approaches. The models are evaluated against human judgments on a semantic similarity task for nine languages. Our strong empirical findings also point to the importance of universality of our graph synset embedding representations with no need for any language-specific adaptation when evaluated on the lexical similarity task. The insights of our exploratory investigation of large-scale colexification graphs could inspire significant advances in NLP across languages, especially for tasks involving languages which lack dedicated lexical resources, and can benefit from language transfer from large shared cross-lingual semantic spaces.

AB - In this paper we focus on patterns of colexification (co-expressions of form-meaning mapping in the lexicon) as an aspect of lexical-semantic organization, and use them to build large scale synset graphs across BabelNet's typologically diverse set of 499 world languages. We introduce and compare several approaches: monolingual and cross-lingual colexification graphs, popular distributional models, and fusion approaches. The models are evaluated against human judgments on a semantic similarity task for nine languages. Our strong empirical findings also point to the importance of universality of our graph synset embedding representations with no need for any language-specific adaptation when evaluated on the lexical similarity task. The insights of our exploratory investigation of large-scale colexification graphs could inspire significant advances in NLP across languages, especially for tasks involving languages which lack dedicated lexical resources, and can benefit from language transfer from large shared cross-lingual semantic spaces.

KW - linguistic typology, senses, synsets, semantics, knowledge transfer, cross-lingual, semantic similarity

UR - http://www.scopus.com/inward/record.url?scp=85138373678&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85138373678&partnerID=8YFLogxK

U2 - 10.18653/v1/2022.naacl-main.386

DO - 10.18653/v1/2022.naacl-main.386

M3 - Conference contribution

AN - SCOPUS:85138373678

SP - 5259

EP - 5270

BT - Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Carpuat, Marine

A2 - de Marneffe, Marie-Catherine

A2 - Meza Ruiz, Ivan Vladimir

PB - Association for Computational Linguistics

T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022

Y2 - 10 July 2022 through 15 July 2022

ER -

Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity

Abstract

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this