Papers › NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition

NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition

12 May 2022arXiv:2205.05832archive 2025-07-28

Shuang Wu, Xiaoning Song, ZhenHua Feng, Xiao-Jun Wu

Recently, Flat-LAttice Transformer (FLAT) has achieved great success in Chinese Named Entity Recognition (NER). FLAT performs lexical enhancement by constructing flat lattices, which mitigates the difficulties posed by blurred word boundaries and the lack of word semantics. In FLAT, the positions of starting and ending characters are used to connect a matching word. However, this method is likely to match more words when dealing with long texts, resulting in long input sequences. Therefore, it significantly increases the memory and computational costs of the self-attention module. To deal with this issue, we advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs by constructing non-flat lattices. Furthermore, with InterFormer as the backbone, we implement NFLAT for Chinese NER. NFLAT decouples lexicon fusion and context feature encoding. Compared with FLAT, it reduces unnecessary attention calculations in "word-character" and "word-word". This reduces the memory usage by about 50% and can use more extensive lexicons or higher batches for network training. The experimental results obtained on several well-known benchmarks demonstrate the superiority of the proposed method over the state-of-the-art hybrid (character-word) models.

PaperPDFCode

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

Code

codermusou/nflat4cner 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 RecognitionNERNamed Entity RecognitionNamed Entity Recognition (NER)named-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chinese Named Entity Recognition MSRA NFLAT F1 94.55 #12 of 21 Archive leaderboard report
Chinese Named Entity Recognition MSRA NFLAT Precision 94.92 #12 of 21 Archive leaderboard report
Chinese Named Entity Recognition MSRA NFLAT Recall 94.19 #12 of 21 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 NFLAT F1 77.21 #10 of 15 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 NFLAT Precision 75.17 #10 of 15 Archive leaderboard report
Chinese Named Entity Recognition OntoNotes 4 NFLAT Recall 79.37 #10 of 15 Archive leaderboard report
Chinese Named Entity Recognition Resume NER NFLAT F1 95.58 #9 of 13 Archive leaderboard report
Chinese Named Entity Recognition Resume NER NFLAT Precision 95.63 #9 of 13 Archive leaderboard report
Chinese Named Entity Recognition Resume NER NFLAT Recall 95.52 #9 of 13 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER NFLAT F1 61.94 #12 of 18 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER NFLAT Precision 59.10 #12 of 18 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER NFLAT Recall 63.76 #12 of 18 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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