Papers › A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
Guanting Dong, Zechen Wang, Jinxu Zhao, Gang Zhao, Daichi Guo, Dayuan Fu, Tingfeng Hui, Chen Zeng, Keqing He, Xuefeng Li, LiWen Wang, Xinyue Cui, Weiran Xu
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.
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) | MSDP | 10 way 1~2 shot | 69.78±0.31 | #1 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTER) | MSDP | 10 way 5~10 shot | 81.50±0.71 | #1 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTER) | MSDP | 5 way 1~2 shot | 76.86±0.22 | #1 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTER) | MSDP | 5 way 5~10 shot | 84.78±0.69 | #1 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | MSDP | 10 way 1~2 shot | 47.13±0.69 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | MSDP | 10 way 5~10 shot | 64.69±0.51 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | MSDP | 5 way 1~2 shot | 56.35±0.28 | #4 of 13 | Archive leaderboard | report |
| Few-shot NER | Few-NERD (INTRA) | MSDP | 5 way 5~10 shot | 66.80±0.78 | #4 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.
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