AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction

Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren


Abstract
Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However, the costs of acquiring such additional information are generally prohibitive. In this paper, we present a novel two-stage framework (AutoTriggER) to improve NER performance by automatically generating and leveraging “entity triggers” which are human-readable cues in the text that help guide the model to make better decisions. Our framework leverages post-hoc explanation to generate rationales and strengthens a model’s prior knowledge using an embedding interpolation technique. This approach allows models to exploit triggers to infer entity boundaries and types instead of solely memorizing the entity words themselves. Through experiments on three well-studied NER datasets, AutoTriggER shows strong label-efficiency, is capable of generalizing to unseen entities, and outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on average.
Anthology ID:
2023.eacl-main.219
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3011–3025
Language:
URL:
https://aclanthology.org/2023.eacl-main.219
DOI:
10.18653/v1/2023.eacl-main.219
Bibkey:
Cite (ACL):
Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, and Xiang Ren. 2023. AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3011–3025, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction (Lee et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.219.pdf
Video:
 https://aclanthology.org/2023.eacl-main.219.mp4