FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition

Linyi Yang, Lifan Yuan, Leyang Cui, Wenyang Gao, Yue Zhang


Abstract
Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years. Existing approaches for few-shot NER are evaluated mainly under in-domain settings. In contrast, little is known about how these inherently faithful models perform in cross-domain NER using a few labeled in-domain examples. This paper proposes a two-step rationale-centric data augmentation method to improve the model’s generalization ability. Results on several datasets show that our model-agnostic method significantly improves the performance of cross-domain NER tasks compared to previous state-of-the-art methods compared to the counterfactual data augmentation and prompt-tuning methods.
Anthology ID:
2022.coling-1.476
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5360–5371
Language:
URL:
https://aclanthology.org/2022.coling-1.476
DOI:
Bibkey:
Cite (ACL):
Linyi Yang, Lifan Yuan, Leyang Cui, Wenyang Gao, and Yue Zhang. 2022. FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5360–5371, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition (Yang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.476.pdf
Code
 lifan-yuan/factmix