Papers › Boundary Smoothing for Named Entity Recognition

Boundary Smoothing for Named Entity Recognition

26 Apr 2022ACL 2022 5arXiv:2204.12031archive 2025-07-28

Enwei Zhu, Jinpeng Li

Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

syuoni/eznlp officialmentioned in paperpytorch 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

Chinese Named Entity RecognitionNERNamed Entity RecognitionNamed Entity Recognition (NER)Nested Named Entity Recognitionnamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chinese Named Entity Recognition MSRA Baseline + BS F1 96.26 #3 of 21 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 Baseline + BS F1 82.83 #3 of 15 Archive leaderboard report
Chinese Named Entity Recognition Resume NER Baseline + BS F1 96.66 #3 of 13 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER Baseline + BS F1 72.66 #2 of 18 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) Baseline + BS F1 93.65 #15 of 73 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) Baseline + BS F1 91.74 #3 of 28 Archive leaderboard report
Nested Named Entity Recognition ACE 2004 Baseline + BS F1 87.98 #8 of 24 Archive leaderboard report
Nested Named Entity Recognition ACE 2005 Baseline + BS F1 87.15 #5 of 25 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

Label Smoothing

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