Papers › DiffusionNER: Boundary Diffusion for Named Entity Recognition
DiffusionNER: Boundary Diffusion for Named Entity Recognition
Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang
In this paper, we propose DiffusionNER, which formulates the named entity recognition task as a boundary-denoising diffusion process and thus generates named entities from noisy spans. During training, DiffusionNER gradually adds noises to the golden entity boundaries by a fixed forward diffusion process and learns a reverse diffusion process to recover the entity boundaries. In inference, DiffusionNER first randomly samples some noisy spans from a standard Gaussian distribution and then generates the named entities by denoising them with the learned reverse diffusion process. The proposed boundary-denoising diffusion process allows progressive refinement and dynamic sampling of entities, empowering DiffusionNER with efficient and flexible entity generation capability. Experiments on multiple flat and nested NER datasets demonstrate that DiffusionNER achieves comparable or even better performance than previous state-of-the-art models.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 |
|---|---|---|---|---|---|---|---|
| Chinese Named Entity Recognition | MSRA | DiffusionNER | F1 | 94.91 | #11 of 21 | Archive leaderboard | report |
| Named Entity Recognition (NER) | ACE 2005 | DiffusionNER | F1 | 86.93 | #6 of 20 | Archive leaderboard | report |
| Named Entity Recognition (NER) | CoNLL 2003 (English) | DiffusionNER | F1 | 92.78 | #36 of 73 | Archive leaderboard | report |
| Named Entity Recognition (NER) | Ontonotes v5 (English) | DiffusionNER | F1 | 90.66 | #9 of 28 | Archive leaderboard | report |
| Nested Named Entity Recognition | ACE 2004 | DiffusionNER | F1 | 88.39 | #4 of 24 | Archive leaderboard | report |
| Nested Named Entity Recognition | GENIA | DiffusionNER | F1 | 81.53 | #2 of 26 | 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