Multilingual Word Sense Disambiguation with Unified Sense Representation

Ying Su, Hongming Zhang, Yangqiu Song, Tong Zhang


Abstract
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the fine-grained semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD systems have achieved impressive performances in English by combining supervised learning with lexical knowledge. However, such success is hard to be replicated in other languages, where we only have very limited annotations. In this paper, based on that the multilingual lexicon BabelNet describing the same set of concepts across languages, we propose to build knowledge and supervised based Multilingual Word Sense Disambiguation (MWSD) systems. We build unified sense representations for multiple languages and address the annotation scarcity problem for MWSD by transferring annotations from rich sourced languages. With the unified sense representations, annotations from multiple languages can be jointly trained to benefit the MWSD tasks. Evaluations of SemEval-13 and SemEval-15 datasets demonstrate the effectiveness of our methodology.
Anthology ID:
2022.coling-1.368
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4193–4202
Language:
URL:
https://aclanthology.org/2022.coling-1.368
DOI:
Bibkey:
Cite (ACL):
Ying Su, Hongming Zhang, Yangqiu Song, and Tong Zhang. 2022. Multilingual Word Sense Disambiguation with Unified Sense Representation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4193–4202, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Multilingual Word Sense Disambiguation with Unified Sense Representation (Su et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.368.pdf
Code
 suytingwan/multilingual-wsd