mlsanityData to 14 Oct 2026

Hierarchically-Refined Label Attention Network for Sequence Labeling

arXiv 1908.08676 ↗First posted 23 Aug 2019cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

CRF has been used as a powerful model for statistical sequence labeling. For neural sequence labeling, however, BiLSTM-CRF does not always lead to better results compared with BiLSTM-softmax local classification. This can be because the simple Markov label transition model of CRF does not give much information gain over strong neural encoding. For better representing label sequences, we investigate a hierarchically-refined label attention network, which explicitly leverages label embeddings and captures potential long-term label dependency by giving each word incrementally refined label distributions with hierarchical attention. Results on POS tagging, NER and CCG supertagging show that the proposed model not only improves the overall tagging accuracy with similar number of parameters, but also significantly speeds up the training and testing compared to BiLSTM-CRF.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 11; 2023: 5; 2024: 1.

25 papers.

Sort:

By area:

  1. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  2. 2021LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Promptingcited by 27
  3. 2022MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Groundingcited by 16
  4. 2021Towards Joint Intent Detection and Slot Filling via Higher-order Attentioncited by 11
  5. 2021An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Fillingcited by 9
  6. 2022A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understandingcited by 9
  7. 2022FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognitioncited by 7
  8. 2022TSAM: A Two-Stream Attention Model for Causal Emotion Entailmentcited by 6
  9. 2022kNN-NER: Named Entity Recognition with Nearest Neighbor Searchcited by 6
  10. 2021Investigating Non-local Features for Neural Constituency Parsingcited by 4
  11. 2023The Temporal Structure of Language Processing in the Human Brain Corresponds to The Layered Hierarchy of Deep Language Modelscited by 4
  12. 2022A Fast Attention Network for Joint Intent Detection and Slot Filling on Edge Devicescited by 3
13 more
  1. 2022GNN-SL: Sequence Labeling Based on Nearest Examples via GNNcited by 3
  2. 2022Distantly supervised end-to-end medical entity extraction from electronic health records with human-level qualitycited by 2
  3. 2023A Persian Benchmark for Joint Intent Detection and Slot Fillingcited by 2
  4. 2023TC-GAT: Graph Attention Network for Temporal Causality Discoverycited by 2
  5. 2023TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognitioncited by 2
  6. 2021Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanismcited by 1
  7. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  8. 2021HAN: Higher-order Attention Network for Spoken Language Understandingcited by 0
  9. 2021Responsive parallelized architecture for deploying deep learning models in production environmentscited by 0
  10. 2022Yunshan Cup 2020: Overview of the Part-of-Speech Tagging Task for Low-resourced Languagescited by 0
  11. 2022Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Fillingcited by 0
  12. 2022A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extractioncited by 0
  13. 2024GWPT: A Green Word-Embedding-based POS Taggercited by 0