Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings

Christos Xypolopoulos, Antoine Tixier, Michalis Vazirgiannis


Abstract
The number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy based on simple geometry in the contextual embedding space. Our approach is fully unsupervised and purely data-driven. Through rigorous experiments, we show that our rankings are well correlated, with strong statistical significance, with 6 different rankings derived from famous human-constructed resources such as WordNet, OntoNotes, Oxford, Wikipedia, etc., for 6 different standard metrics. We also visualize and analyze the correlation between the human rankings and make interesting observations. A valuable by-product of our method is the ability to sample, at no extra cost, sentences containing different senses of a given word. Finally, the fully unsupervised nature of our approach makes it applicable to any language. Code and data are publicly available https://github.com/ksipos/polysemy-assessment .
Anthology ID:
2021.eacl-main.297
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3391–3401
Language:
URL:
https://aclanthology.org/2021.eacl-main.297
DOI:
10.18653/v1/2021.eacl-main.297
Bibkey:
Cite (ACL):
Christos Xypolopoulos, Antoine Tixier, and Michalis Vazirgiannis. 2021. Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3391–3401, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings (Xypolopoulos et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.297.pdf
Code
 ksipos/polysemy-assessment