Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation

Daniel Loureiro, Alípio Jorge


Abstract
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that contextual embeddings can be used to achieve unprecedented gains in Word Sense Disambiguation (WSD) tasks. Our approach focuses on creating sense-level embeddings with full-coverage of WordNet, and without recourse to explicit knowledge of sense distributions or task-specific modelling. As a result, a simple Nearest Neighbors (k-NN) method using our representations is able to consistently surpass the performance of previous systems using powerful neural sequencing models. We also analyse the robustness of our approach when ignoring part-of-speech and lemma features, requiring disambiguation against the full sense inventory, and revealing shortcomings to be improved. Finally, we explore applications of our sense embeddings for concept-level analyses of contextual embeddings and their respective NLMs.
Anthology ID:
P19-1569
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5682–5691
Language:
URL:
https://aclanthology.org/P19-1569
DOI:
10.18653/v1/P19-1569
Bibkey:
Cite (ACL):
Daniel Loureiro and Alípio Jorge. 2019. Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5682–5691, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation (Loureiro & Jorge, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1569.pdf
Video:
 https://aclanthology.org/P19-1569.mp4
Code
 danlou/LMMS
Data
Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison