SenseBERT: Driving Some Sense into BERT

Yoav Levine, Barak Lenz, Or Dagan, Ori Ram, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham


Abstract
The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision techniques operate at the word form level, which serves as a surrogate for the underlying semantic content. This paper proposes a method to employ weak-supervision directly at the word sense level. Our model, named SenseBERT, is pre-trained to predict not only the masked words but also their WordNet supersenses. Accordingly, we attain a lexical-semantic level language model, without the use of human annotation. SenseBERT achieves significantly improved lexical understanding, as we demonstrate by experimenting on SemEval Word Sense Disambiguation, and by attaining a state of the art result on the ‘Word in Context’ task.
Anthology ID:
2020.acl-main.423
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:
4656–4667
Language:
URL:
https://aclanthology.org/2020.acl-main.423
DOI:
10.18653/v1/2020.acl-main.423
Bibkey:
Cite (ACL):
Yoav Levine, Barak Lenz, Or Dagan, Ori Ram, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, and Yoav Shoham. 2020. SenseBERT: Driving Some Sense into BERT. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4656–4667, Online. Association for Computational Linguistics.
Cite (Informal):
SenseBERT: Driving Some Sense into BERT (Levine et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.423.pdf
Video:
 http://slideslive.com/38929368
Data
GLUEQNLIRTESuperGLUEWiC