Masked language models directly encode linguistic uncertainty

Cassandra L. Jacobs, Ryan J. Hubbard, Kara D. Federmeier


Anthology ID:
2022.scil-1.22
Volume:
Proceedings of the Society for Computation in Linguistics 2022
Month:
February
Year:
2022
Address:
online
Editors:
Allyson Ettinger, Tim Hunter, Brandon Prickett
Venue:
SCiL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
225–228
Language:
URL:
https://aclanthology.org/2022.scil-1.22
DOI:
Bibkey:
Cite (ACL):
Cassandra L. Jacobs, Ryan J. Hubbard, and Kara D. Federmeier. 2022. Masked language models directly encode linguistic uncertainty. In Proceedings of the Society for Computation in Linguistics 2022, pages 225–228, online. Association for Computational Linguistics.
Cite (Informal):
Masked language models directly encode linguistic uncertainty (Jacobs et al., SCiL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.scil-1.22.pdf