Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration

Simone Conia, Roberto Navigli


Abstract
Recent studies treat Word Sense Disambiguation (WSD) as a single-label classification problem in which one is asked to choose only the best-fitting sense for a target word, given its context. However, gold data labelled by expert annotators suggest that maximizing the probability of a single sense may not be the most suitable training objective for WSD, especially if the sense inventory of choice is fine-grained. In this paper, we approach WSD as a multi-label classification problem in which multiple senses can be assigned to each target word. Not only does our simple method bear a closer resemblance to how human annotators disambiguate text, but it can also be seamlessly extended to exploit structured knowledge from semantic networks to achieve state-of-the-art results in English all-words WSD.
Anthology ID:
2021.eacl-main.286
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3269–3275
Language:
URL:
https://aclanthology.org/2021.eacl-main.286
DOI:
10.18653/v1/2021.eacl-main.286
Bibkey:
Cite (ACL):
Simone Conia and Roberto Navigli. 2021. Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3269–3275, Online. Association for Computational Linguistics.
Cite (Informal):
Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration (Conia & Navigli, EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.286.pdf
Code
 sapienzanlp/multilabel-wsd
Data
Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison