Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model

Hongliang Dai, Yangqiu Song, Haixun Wang


Abstract
Recently, there is an effort to extend fine-grained entity typing by using a richer and ultra-fine set of types, and labeling noun phrases including pronouns and nominal nouns instead of just named entity mentions. A key challenge for this ultra-fine entity typing task is that human annotated data are extremely scarce, and the annotation ability of existing distant or weak supervision approaches is very limited. To remedy this problem, in this paper, we propose to obtain training data for ultra-fine entity typing by using a BERT Masked Language Model (MLM). Given a mention in a sentence, our approach constructs an input for the BERT MLM so that it predicts context dependent hypernyms of the mention, which can be used as type labels. Experimental results demonstrate that, with the help of these automatically generated labels, the performance of an ultra-fine entity typing model can be improved substantially. We also show that our approach can be applied to improve traditional fine-grained entity typing after performing simple type mapping.
Anthology ID:
2021.acl-long.141
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1790–1799
Language:
URL:
https://aclanthology.org/2021.acl-long.141
DOI:
10.18653/v1/2021.acl-long.141
Bibkey:
Cite (ACL):
Hongliang Dai, Yangqiu Song, and Haixun Wang. 2021. Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1790–1799, Online. Association for Computational Linguistics.
Cite (Informal):
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model (Dai et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.141.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.141.mp4
Code
 HKUST-KnowComp/MLMET
Data
OntoNotes 5.0Open Entity