Let’s Play Mono-Poly: BERT Can Reveal Words’ Polysemy Level and Partitionability into Senses

Aina Garí Soler, Marianna Apidianaki


Abstract
Pre-trained language models (LMs) encode rich information about linguistic structure but their knowledge about lexical polysemy remains unclear. We propose a novel experimental setup for analyzing this knowledge in LMs specifically trained for different languages (English, French, Spanish, and Greek) and in multilingual BERT. We perform our analysis on datasets carefully designed to reflect different sense distributions, and control for parameters that are highly correlated with polysemy such as frequency and grammatical category. We demonstrate that BERT-derived representations reflect words’ polysemy level and their partitionability into senses. Polysemy-related information is more clearly present in English BERT embeddings, but models in other languages also manage to establish relevant distinctions between words at different polysemy levels. Our results contribute to a better understanding of the knowledge encoded in contextualized representations and open up new avenues for multilingual lexical semantics research.
Anthology ID:
2021.tacl-1.50
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
825–844
Language:
URL:
https://aclanthology.org/2021.tacl-1.50
DOI:
10.1162/tacl_a_00400
Bibkey:
Cite (ACL):
Aina Garí Soler and Marianna Apidianaki. 2021. Let’s Play Mono-Poly: BERT Can Reveal Words’ Polysemy Level and Partitionability into Senses. Transactions of the Association for Computational Linguistics, 9:825–844.
Cite (Informal):
Let’s Play Mono-Poly: BERT Can Reveal Words’ Polysemy Level and Partitionability into Senses (Garí Soler & Apidianaki, TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.50.pdf
Video:
 https://aclanthology.org/2021.tacl-1.50.mp4