A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense Disambiguation

Ming Wang, Yinglin Wang


Abstract
Contextual embeddings are proved to be overwhelmingly effective to the task of Word Sense Disambiguation (WSD) compared with other sense representation techniques. However, these embeddings fail to embed sense knowledge in semantic networks. In this paper, we propose a Synset Relation-Enhanced Framework (SREF) that leverages sense relations for both sense embedding enhancement and a try-again mechanism that implements WSD again, after obtaining basic sense embeddings from augmented WordNet glosses. Experiments on all-words and lexical sample datasets show that the proposed system achieves new state-of-the-art results, defeating previous knowledge-based systems by at least 5.5 F1 measure. When the system utilizes sense embeddings learned from SemCor, it outperforms all previous supervised systems with only 20% SemCor data.
Anthology ID:
2020.emnlp-main.504
Original:
2020.emnlp-main.504v1
Version 2:
2020.emnlp-main.504v2
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6229–6240
Language:
URL:
https://aclanthology.org/2020.emnlp-main.504
DOI:
10.18653/v1/2020.emnlp-main.504
Bibkey:
Cite (ACL):
Ming Wang and Yinglin Wang. 2020. A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense Disambiguation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6229–6240, Online. Association for Computational Linguistics.
Cite (Informal):
A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense Disambiguation (Wang & Wang, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.504.pdf
Video:
 https://slideslive.com/38938678