Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification

Rami Aly, Andreas Vlachos, Ryan McDonald


Abstract
A common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for the target entity classes during training. Zero-shot learning approaches address this issue by learning models from classes with training data that can predict classes without it. This paper presents the first approach for zero-shot NERC, introducing novel architectures that leverage the fact that textual descriptions for many entity classes occur naturally. We address the zero-shot NERC specific challenge that the not-an-entity class is not well defined as different entity classes are considered in training and testing. For evaluation, we adapt two datasets, OntoNotes and MedMentions, emulating the difficulty of real-world zero-shot learning by testing models on the rarest entity classes. Our proposed approach outperforms baselines adapted from machine reading comprehension and zero-shot text classification. Furthermore, we assess the effect of different class descriptions for this task.
Anthology ID:
2021.acl-long.120
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
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1516–1528
Language:
URL:
https://aclanthology.org/2021.acl-long.120
DOI:
10.18653/v1/2021.acl-long.120
Bibkey:
Cite (ACL):
Rami Aly, Andreas Vlachos, and Ryan McDonald. 2021. Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification. 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 1516–1528, Online. Association for Computational Linguistics.
Cite (Informal):
Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification (Aly et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.120.pdf
Video:
 https://aclanthology.org/2021.acl-long.120.mp4
Data
MedMentionsOntoNotes 5.0