mlsanityData to 7 Oct 2026

FLAT: Chinese NER Using Flat-Lattice Transformer

arXiv 2004.11795 ↗First posted 24 Apr 2020cs.CLcited by 67

Not on the map. Why?

Abstract (arXiv)

Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, since the lattice structure is complex and dynamic, most existing lattice-based models are hard to fully utilize the parallel computation of GPUs and usually have a low inference-speed. In this paper, we propose FLAT: Flat-LAttice Transformer for Chinese NER, which converts the lattice structure into a flat structure consisting of spans. Each span corresponds to a character or latent word and its position in the original lattice. With the power of Transformer and well-designed position encoding, FLAT can fully leverage the lattice information and has an excellent parallelization ability. Experiments on four datasets show FLAT outperforms other lexicon-based models in performance and efficiency.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 28; 2023: 7; 2024: 7; 2025: 2; 2026: 1.

67 papers.

Sort:

By area:

  1. 2021A Survey of Transformerscited by 399
  2. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  3. 2021Unified Named Entity Recognition as Word-Word Relation Classificationcited by 89
  4. 2021CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generationcited by 81
  5. 2021Locate and Label: A Two-stage Identifier for Nested Named Entity Recognitioncited by 60
  6. 2021Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphscited by 44
  7. 2021Lexicon Enhanced Chinese Sequence Labeling Using BERT Adaptercited by 34
  8. 2021TaCL: Improving BERT Pre-training with Token-aware Contrastive Learningcited by 32
  9. 2021Link Prediction on N-ary Relational Facts: A Graph-based Approachcited by 29
  10. 2022Boundary Smoothing for Named Entity Recognitioncited by 21
  11. 2021Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Modelscited by 19
  12. 2022AISHELL-NER: Named Entity Recognition from Chinese Speechcited by 19
38 more
  1. 2022Parallel Instance Query Network for Named Entity Recognitioncited by 19
  2. 2021LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matchingcited by 15
  3. 2023FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval systemcited by 15
  4. 2022TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizercited by 13
  5. 2021MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognitioncited by 11
  6. 2022PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasetscited by 10
  7. 2021Knowledge Enhanced Sports Game Summarizationcited by 9
  8. 2021AliMe MKG: A Multi-modal Knowledge Graph for Live-streaming E-commercecited by 8
  9. 2022Flat Multi-modal Interaction Transformer for Named Entity Recognitioncited by 8
  10. 2023Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NERcited by 8
  11. 2022Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognitioncited by 7
  12. 2021Masked Conditional Random Fields for Sequence Labelingcited by 6
  13. 2023Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation Extractioncited by 6
  14. 2021FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networkscited by 5
  15. 2021MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attentioncited by 5
  16. 2024Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challengescited by 5
  17. 2021DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labelingcited by 4
  18. 2022TURNER: The Uncertainty-based Retrieval Framework for Chinese NERcited by 4
  19. 2022ANEC: An Amharic Named Entity Corpus and Transformer Based Recognizercited by 4
  20. 2022Deep Span Representations for Named Entity Recognitioncited by 4
  21. 2022Robust Self-Augmentation for Named Entity Recognition with Meta Reweightingcited by 3
  22. 2023The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POScited by 3
  23. 2024KnowCoder-X: Boosting Multilingual Information Extraction via Codecited by 3
  24. 2021Lex-BERT: Enhancing BERT based NER with lexiconscited by 2
  25. 2022MarkBERT: Marking Word Boundaries Improves Chinese BERTcited by 2
  26. 2022An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformercited by 2
  27. 2022Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognitioncited by 2
  28. 2022gBuilder: A Scalable Knowledge Graph Construction System for Unstructured Corpuscited by 2
  29. 2022TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learningcited by 2
  30. 2022Lexicon-injected Semantic Parsing for Task-Oriented Dialogcited by 2
  31. 2022Statistical Dataset Evaluation: Reliability, Difficulty, and Validitycited by 2
  32. 2024Shapley Value-based Contrastive Alignment for Multimodal Information Extractioncited by 2
  33. 2024LLM-DER:A Named Entity Recognition Method Based on Large Language Models for Chinese Coal Chemical Domaincited by 2
  34. 2021LT-LM: a novel non-autoregressive language model for single-shot lattice rescoringcited by 1
  35. 2022Rethinking the Value of Gazetteer in Chinese Named Entity Recognitioncited by 1
  36. 2024RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalizationcited by 1
  37. 2021To Understand Representation of Layer-aware Sequence Encoders as Multi-order-graphcited by 0
  38. 2021AdaK-NER: An Adaptive Top-K Approach for Named Entity Recognition with Incomplete Annotationscited by 0

50 most cited of 67 All 67 (JSON)