SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER

Shuzheng Si, Shuang Zeng, Jiaxing Lin, Baobao Chang


Abstract
Unlabeled Entity Problem (UEP) in Named Entity Recognition (NER) datasets seriously hinders the improvement of NER performance. This paper proposes SCL-RAI to cope with this problem. Firstly, we decrease the distance of span representations with the same label while increasing it for different ones via span-based contrastive learning, which relieves the ambiguity among entities and improves the robustness of the model over unlabeled entities. Then we propose retrieval augmented inference to mitigate the decision boundary shifting problem. Our method significantly outperforms the previous SOTA method by 4.21% and 8.64% F1-score on two real-world datasets.
Anthology ID:
2022.coling-1.202
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:
2313–2318
Language:
URL:
https://aclanthology.org/2022.coling-1.202
DOI:
Bibkey:
Cite (ACL):
Shuzheng Si, Shuang Zeng, Jiaxing Lin, and Baobao Chang. 2022. SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2313–2318, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER (Si et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.202.pdf
Code
 pkunlp-icler/scl-rai