Papers › Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER

Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER

29 Aug 2019arXiv:1908.11046archive 2025-07-28

Peng-Hsuan Li, Tsu-Jui Fu, Wei-Yun Ma

BiLSTM has been prevalently used as a core module for NER in a sequence-labeling setup. State-of-the-art approaches use BiLSTM with additional resources such as gazetteers, language-modeling, or multi-task supervision to further improve NER. This paper instead takes a step back and focuses on analyzing problems of BiLSTM itself and how exactly self-attention can bring improvements. We formally show the limitation of (CRF-)BiLSTM in modeling cross-context patterns for each word -- the XOR limitation. Then, we show that two types of simple cross-structures -- self-attention and Cross-BiLSTM -- can effectively remedy the problem. We test the practical impacts of the deficiency on real-world NER datasets, OntoNotes 5.0 and WNUT 2017, with clear and consistent improvements over the baseline, up to 8.7% on some of the multi-token entity mentions. We give in-depth analyses of the improvements across several aspects of NER, especially the identification of multi-token mentions. This study should lay a sound foundation for future improvements on sequence-labeling NER. (Source codes: https://github.com/jacobvsdanniel/cross-ner)

PaperPDFCode

Code

jacobvsdanniel/cross-ner officialmentioned in papermentioned on GitHubtf report
jacobvsdanniel/cross_ner officialmentioned in papermentioned on GitHubtf report
ckiplab/ckiptagger mentioned on GitHubtf 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

Language ModelingNERNamed Entity Recognition (NER)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Named Entity Recognition (NER) Ontonotes v5 (English) Att-BiLSTM-CNN F1 88.4 #20 of 28 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) Att-BiLSTM-CNN Precision 88.71 #20 of 28 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) Att-BiLSTM-CNN Recall 88.11 #20 of 28 Archive leaderboard report
Named Entity Recognition (NER) WNUT 2017 Cross-BiLSTM-CNN F1 42.85 #20 of 23 Archive leaderboard report
Named Entity Recognition (NER) WNUT 2017 Cross-BiLSTM-CNN Precision 58.28 #20 of 23 Archive leaderboard report
Named Entity Recognition (NER) WNUT 2017 Cross-BiLSTM-CNN Recall 33.92 #20 of 23 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

BiLSTMLSTMSigmoid ActivationTanh Activation

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