Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings

Mattia Proietti, Gianluca Lebani, Alessandro Lenci


Abstract
Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence. Such models have been shown to achieve a state-of-the-art performance on a wide variety of tasks. Yet, the community struggles in understanding what kind of semantic knowledge these representations encode. We report a series of experiments aimed at investigating to what extent one of such models, BERT, is able to infer the semantic relations that, according to Dowty’s Proto-Roles theory, a verbal argument receives by virtue of its role in the event described by the verb. This hypothesis were put to test by learning a linear mapping from the BERT’s verb embeddings to an interpretable space of semantic properties built from the linguistic dataset by White et al. (2016). In a first experiment we tested whether the semantic properties inferred from a typed version of the BERT embeddings would be more linguistically plausible than those produced by relying on static embeddings. We then move to evaluate the semantic properties inferred from the contextual embeddings both against those available in the original dataset, as well as by assessing their ability to model the semantic properties possessed by the agent of the verbs participating in the so-called causative alternation.
Anthology ID:
2022.coling-1.360
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4101–4112
Language:
URL:
https://aclanthology.org/2022.coling-1.360
DOI:
Bibkey:
Cite (ACL):
Mattia Proietti, Gianluca Lebani, and Alessandro Lenci. 2022. Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4101–4112, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings (Proietti et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.360.pdf