Papers › Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition

Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition

13 Feb 2023arXiv:2302.06397archive 2025-07-28

Yongqi Li, Yu Yu, Tieyun Qian

Despite the recent success achieved by several two-stage prototypical networks in few-shot named entity recognition (NER) task, the overdetected false spans at the span detection stage and the inaccurate and unstable prototypes at the type classification stage remain to be challenging problems. In this paper, we propose a novel Type-Aware Decomposed framework, namely TadNER, to solve these problems. We first present a type-aware span filtering strategy to filter out false spans by removing those semantically far away from type names. We then present a type-aware contrastive learning strategy to construct more accurate and stable prototypes by jointly exploiting support samples and type names as references. Extensive experiments on various benchmarks prove that our proposed TadNER framework yields a new state-of-the-art performance. Our code and data will be available at https://github.com/NLPWM-WHU/TadNER.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

liyongqi2002/TadNER officialmentioned in papermentioned on GitHubpytorch report
nlpwm-whu/tadner officialmentioned in papermentioned on GitHubpytorch report

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

Contrastive LearningFew-shot NERNERNamed Entity RecognitionNamed Entity Recognition (NER)named-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-shot NER Few-NERD (INTER) TadNER 10 way 1~2 shot 64.06±0.19 #5 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) TadNER 10 way 5~10 shot 69.94±0.15 #5 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) TadNER 5 way 1~2 shot 64.83±0.14 #5 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) TadNER 5 way 5~10 shot 72.12±0.12 #5 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) TadNER 10 way 1~2 shot 55.44±0.08 #3 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) TadNER 10 way 5~10 shot 60.87±0.22 #3 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) TadNER 5 way 1~2 shot 60.78±0.32 #3 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) TadNER 5 way 5~10 shot 67.94±0.17 #3 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

Contrastive Learning

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