Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

Xiangji Zeng, Yunliang Li, Yuchen Zhai, Yin Zhang


Abstract
Past progress on neural models has proven that named entity recognition is no longer a problem if we have enough labeled data. However, collecting enough data and annotating them are labor-intensive, time-consuming, and expensive. In this paper, we decompose the sentence into two parts: entity and context, and rethink the relationship between them and model performance from a causal perspective. Based on this, we propose the Counterfactual Generator, which generates counterfactual examples by the interventions on the existing observational examples to enhance the original dataset. Experiments across three datasets show that our method improves the generalization ability of models under limited observational examples. Besides, we provide a theoretical foundation by using a structural causal model to explore the spurious correlations between input features and output labels. We investigate the causal effects of entity or context on model performance under both conditions: the non-augmented and the augmented. Interestingly, we find that the non-spurious correlations are more located in entity representation rather than context representation. As a result, our method eliminates part of the spurious correlations between context representation and output labels. The code is available at https://github.com/xijiz/cfgen.
Anthology ID:
2020.emnlp-main.590
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7270–7280
Language:
URL:
https://aclanthology.org/2020.emnlp-main.590
DOI:
10.18653/v1/2020.emnlp-main.590
Bibkey:
Cite (ACL):
Xiangji Zeng, Yunliang Li, Yuchen Zhai, and Yin Zhang. 2020. Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7270–7280, Online. Association for Computational Linguistics.
Cite (Informal):
Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition (Zeng et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.590.pdf
Video:
 https://slideslive.com/38938699
Code
 xijiz/cfgen