Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings

Chenxin Liu, Emmanuele Chersoni


Abstract
The distinction between mass nouns and count nouns has a long history in formal semantics, and linguists have been trying to identify the semantic properties defining the two classes. However, they also recognized that both can undergo meaning shifts and be used in contexts of a different type, via nominal coercion. In this paper, we present an approach to measure the meaning shift in count-mass coercion in English that makes use of static and contextualized word embedding distance. Our results show that the coercion shifts are detected only by a small subset of the traditional word embedding models, and that the shifts detected by the contextualized embedding of BERT are more pronounced for mass nouns.
Anthology ID:
2022.cogalex-1.7
Volume:
Proceedings of the Workshop on Cognitive Aspects of the Lexicon
Month:
November
Year:
2022
Address:
Taipei, Taiwan
Editors:
Michael Zock, Emmanuele Chersoni, Yu-Yin Hsu, Enrico Santus
Venue:
CogALex
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
49–57
Language:
URL:
https://aclanthology.org/2022.cogalex-1.7
DOI:
10.18653/v1/2022.cogalex-1.7
Bibkey:
Cite (ACL):
Chenxin Liu and Emmanuele Chersoni. 2022. Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings. In Proceedings of the Workshop on Cognitive Aspects of the Lexicon, pages 49–57, Taipei, Taiwan. Association for Computational Linguistics.
Cite (Informal):
Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings (Liu & Chersoni, CogALex 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.cogalex-1.7.pdf