Negation, Coordination, and Quantifiers in Contextualized Language Models

Aikaterini-Lida Kalouli, Rita Sevastjanova, Christin Beck, Maribel Romero


Abstract
With the success of contextualized language models, much research explores what these models really learn and in which cases they still fail. Most of this work focuses on specific NLP tasks and on the learning outcome. Little research has attempted to decouple the models’ weaknesses from specific tasks and focus on the embeddings per se and their mode of learning. In this paper, we take up this research opportunity: based on theoretical linguistic insights, we explore whether the semantic constraints of function words are learned and how the surrounding context impacts their embeddings. We create suitable datasets, provide new insights into the inner workings of LMs vis-a-vis function words and implement an assisting visual web interface for qualitative analysis.
Anthology ID:
2022.coling-1.272
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3074–3085
Language:
URL:
https://aclanthology.org/2022.coling-1.272
DOI:
Bibkey:
Cite (ACL):
Aikaterini-Lida Kalouli, Rita Sevastjanova, Christin Beck, and Maribel Romero. 2022. Negation, Coordination, and Quantifiers in Contextualized Language Models. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3074–3085, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Negation, Coordination, and Quantifiers in Contextualized Language Models (Kalouli et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.272.pdf
Data
LAMA