Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity

John Harvill, Roxana Girju, Mark Hasegawa-Johnson


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.
Anthology ID:
2022.naacl-main.386
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5259–5270
Language:
URL:
https://aclanthology.org/2022.naacl-main.386
DOI:
10.18653/v1/2022.naacl-main.386
Bibkey:
Cite (ACL):
John Harvill, Roxana Girju, and Mark Hasegawa-Johnson. 2022. Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5259–5270, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity (Harvill et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.386.pdf
Software:
 2022.naacl-main.386.software.zip
Code
 jharvill23/syn2vec