SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER
This addresses a specific bottleneck in NER datasets for researchers and practitioners, offering a novel method to handle unlabeled entities, though it appears incremental as it builds on existing contrastive learning and retrieval techniques.
The paper tackled the Unlabeled Entity Problem in Named Entity Recognition by proposing SCL-RAI, which uses span-based contrastive learning and retrieval augmented inference to improve robustness and mitigate decision boundary shifting, achieving F1-score gains of 4.21% and 8.64% over previous SOTA on two datasets.
Named Entity Recognition is the task to locate and classify the entities in the text. However, Unlabeled Entity Problem in 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.