Game Theory Meets Embeddings: a Unified Framework for Word Sense Disambiguation

Rocco Tripodi, Roberto Navigli


Abstract
Game-theoretic models, thanks to their intrinsic ability to exploit contextual information, have shown to be particularly suited for the Word Sense Disambiguation task. They represent ambiguous words as the players of a non cooperative game and their senses as the strategies that the players can select in order to play the games. The interaction among the players is modeled with a weighted graph and the payoff as an embedding similarity function, that the players try to maximize. The impact of the word and sense embedding representations in the framework has been tested and analyzed extensively: experiments on standard benchmarks show state-of-art performances and different tests hint at the usefulness of using disambiguation to obtain contextualized word representations.
Anthology ID:
D19-1009
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
88–99
Language:
URL:
https://aclanthology.org/D19-1009
DOI:
10.18653/v1/D19-1009
Bibkey:
Cite (ACL):
Rocco Tripodi and Roberto Navigli. 2019. Game Theory Meets Embeddings: a Unified Framework for Word Sense Disambiguation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 88–99, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Game Theory Meets Embeddings: a Unified Framework for Word Sense Disambiguation (Tripodi & Navigli, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1009.pdf