Papers › Unified Named Entity Recognition as Word-Word Relation Classification

Unified Named Entity Recognition as Word-Word Relation Classification

19 Dec 2021arXiv:2112.10070archive 2025-07-28

Jingye Li, Hao Fei, Jiang Liu, Shengqiong Wu, Meishan Zhang, Chong Teng, Donghong Ji, Fei Li

So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka. nested), and discontinuous NER, which have mostly been studied individually. Recently, a growing interest has been built for unified NER, tackling the above three jobs concurrently with one single model. Current best-performing methods mainly include span-based and sequence-to-sequence models, where unfortunately the former merely focus on boundary identification and the latter may suffer from exposure bias. In this work, we present a novel alternative by modeling the unified NER as word-word relation classification, namely W^2NER. The architecture resolves the kernel bottleneck of unified NER by effectively modeling the neighboring relations between entity words with Next-Neighboring-Word (NNW) and Tail-Head-Word-* (THW-*) relations. Based on the W^2NER scheme we develop a neural framework, in which the unified NER is modeled as a 2D grid of word pairs. We then propose multi-granularity 2D convolutions for better refining the grid representations. Finally, a co-predictor is used to sufficiently reason the word-word relations. We perform extensive experiments on 14 widely-used benchmark datasets for flat, overlapped, and discontinuous NER (8 English and 6 Chinese datasets), where our model beats all the current top-performing baselines, pushing the state-of-the-art performances of unified NER.

PaperPDFCode

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

Code

ljynlp/w2ner 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

Chinese Named Entity RecognitionClassificationNERNamed Entity RecognitionNamed Entity Recognition (NER)Nested Named Entity RecognitionRelation Classificationnamed-entity-recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chinese Named Entity Recognition MSRA W2NER F1 96.10 #4 of 21 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 W2NER F1 83.08 #2 of 15 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) W2NER F1 93.07 #32 of 73 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) W2NER F1 90.50 #10 of 28 Archive leaderboard report
Nested Named Entity Recognition ACE 2004 W2NER F1 87.52 #10 of 24 Archive leaderboard report
Nested Named Entity Recognition ACE 2005 W2NER F1 86.79 #8 of 25 Archive leaderboard report
Nested Named Entity Recognition GENIA W2NER F1 81.39 #4 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.

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