Probing for Referential Information in Language Models

Ionut-Teodor Sorodoc, Kristina Gulordava, Gemma Boleda


Abstract
Language models keep track of complex information about the preceding context – including, e.g., syntactic relations in a sentence. We investigate whether they also capture information beneficial for resolving pronominal anaphora in English. We analyze two state of the art models with LSTM and Transformer architectures, via probe tasks and analysis on a coreference annotated corpus. The Transformer outperforms the LSTM in all analyses. Our results suggest that language models are more successful at learning grammatical constraints than they are at learning truly referential information, in the sense of capturing the fact that we use language to refer to entities in the world. However, we find traces of the latter aspect, too.
Anthology ID:
2020.acl-main.384
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4177–4189
Language:
URL:
https://aclanthology.org/2020.acl-main.384
DOI:
10.18653/v1/2020.acl-main.384
Bibkey:
Cite (ACL):
Ionut-Teodor Sorodoc, Kristina Gulordava, and Gemma Boleda. 2020. Probing for Referential Information in Language Models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4177–4189, Online. Association for Computational Linguistics.
Cite (Informal):
Probing for Referential Information in Language Models (Sorodoc et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.384.pdf
Video:
 http://slideslive.com/38929145