Abstract
Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dictionary bias, we conduct backdoor adjustment to remove the spurious correlations introduced by the dictionary confounder. For inter-dictionary bias, we propose a causal invariance regularizer which will make DS-NER models more robust to the perturbation of dictionaries. Experiments on four datasets and three DS-NER models show that our method can significantly improve the performance of DS-NER.- Anthology ID:
- 2021.acl-long.371
- 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:
- 4803–4813
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.371
- DOI:
- 10.18653/v1/2021.acl-long.371
- Cite (ACL):
- Wenkai Zhang, Hongyu Lin, Xianpei Han, and Le Sun. 2021. De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention. 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 4803–4813, Online. Association for Computational Linguistics.
- Cite (Informal):
- De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention (Zhang et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.371.pdf
- Code
- zwkatgithub/DSCAU
- Data
- CoNLL 2003