Papers › HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot...
HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition
Wei Chen, Lili Zhao, Pengfei Luo, Tong Xu, Yi Zheng, Enhong Chen
Few-shot Named Entity Recognition (NER) task, which aims to identify and classify entities from different domains with limited training samples, has long been treated as a basic step for knowledge graph (KG) construction. Great efforts have been made on this task with competitive performance, however, they usually treat the two subtasks, namely span detection and type classification, as mutually independent, and the integrity and correlation between subtasks have been largely ignored. Moreover, prior arts may fail to absorb the coarse-grained features of entities, resulting in a semantic-insufficient representation of entity types. To that end, in this paper, we propose a Hierarchical Enhancing ProtoNet (HEProto) based on multi-task learning, which is utilized to jointly learn these two subtasks and model their correlation. Specifically, we adopt contrastive learning to enhance the span boundary information and the type semantic representations in these two subtasks. Then, the hierarchical prototypical network is designed to leverage the coarse-grained information of entities in the type classification stage, which could help the model to better learn the fine-grained semantic representations. Along this line, we construct a similarity margin loss to reduce the similarity between fine-grained entities and other irrelevant coarse-grained prototypes. Finally, extensive experiments on the Few-NERD dataset prove that our solution outperforms competitive baseline methods. The source code of HEProto is available at https://github.com/fanshu6hao/HEProto.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Few-shot NER | Few-NERD (INTER) | HEProto | 10 way 1~2 shot | 60.91±0.20 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTER) | HEProto | 10 way 5~10 shot | 68.92±0.20 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTER) | HEProto | 5 way 1~2 shot | 66.40±0.18 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTER) | HEProto | 5 way 5~10 shot | 72.53±0.11 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | HEProto | 10 way 1~2 shot | 46.45±0.21 | #5 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | HEProto | 10 way 5~10 shot | 58.98±0.22 | #5 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | HEProto | 5 way 1~2 shot | 53.03±0.30 | #5 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | HEProto | 5 way 5~10 shot | 65.70±0.21 | #5 of 13 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections