mlsanityData to 7 Oct 2026

SpanNER: Named Entity Re-/Recognition as Span Prediction

arXiv 2106.00641 ↗First posted 1 Jun 2021cs.CLcited by 55

Not on the map. Why?

Abstract (arXiv)

Recent years have seen the paradigm shift of Named Entity Recognition (NER) systems from sequence labeling to span prediction. Despite its preliminary effectiveness, the span prediction model's architectural bias has not been fully understood. In this paper, we first investigate the strengths and weaknesses when the span prediction model is used for named entity recognition compared with the sequence labeling framework and how to further improve it, which motivates us to make complementary advantages of systems based on different paradigms. We then reveal that span prediction, simultaneously, can serve as a system combiner to re-recognize named entities from different systems' outputs. We experimentally implement 154 systems on 11 datasets, covering three languages, comprehensive results show the effectiveness of span prediction models that both serve as base NER systems and system combiners. We make all code and datasets available: urlhttps://github.com/neulab/spanner, as well as an online system demo: urlhttp://spanner.sh. Our model also has been deployed into the ExplainaBoard platform, which allows users to flexibly perform a system combination of top-scoring systems in an interactive way: urlhttp://explainaboard.nlpedia.ai/leaderboard/task-ner/.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 28 of its 65 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

28 of 65 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2018Deep contextualized word representationscited by 2,285
  5. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  6. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  7. 2019Text Summarization with Pretrained Encoderscited by 553
  8. 2016Neural Architectures for Named Entity Recognitioncited by 548
  9. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 544
  10. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  11. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  12. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
16 more
  1. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  2. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  3. 2020Named Entity Recognition as Dependency Parsingcited by 150
  4. 2017A Minimal Span-Based Neural Constituency Parsercited by 59
  5. 2021ExplainaBoard: An Explainable Leaderboard for NLPcited by 50
  6. 2020Rethinking Generalization of Neural Models: A Named Entity Recognition Case Studycited by 35
  7. 2019Hierarchical Contextualized Representation for Named Entity Recognitioncited by 32
  8. 2020TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognitioncited by 30
  9. 2020Interpretable Multi-dataset Evaluation for Named Entity Recognitioncited by 27
  10. 2020Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognitioncited by 23
  11. 2019Generalizing Natural Language Analysis through Span-relation Representationscited by 22
  12. 2019Multi-Grained Named Entity Recognitioncited by 19
  13. 2019GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognitioncited by 18
  14. 2018Robust Lexical Features for Improved Neural Network Named-Entity Recognitioncited by 12
  15. 2017Neural System Combination for Machine Translationcited by 6
  16. 2021Larger-Context Tagging: When and Why Does It Work?cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 15; 2023: 19; 2024: 9; 2025: 6; 2026: 2.

55 papers.

Sort:

By area:

  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  2. 2023GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformercited by 84
  3. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  4. 2021Packed Levitated Marker for Entity and Relation Extractioncited by 49
  5. 2021Paradigm Shift in Natural Language Processingcited by 39
  6. 2021Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labelingcited by 25
  7. 2022Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learningcited by 24
  8. 2022Decomposed Meta-Learning for Few-Shot Named Entity Recognitioncited by 22
  9. 2022MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspectivecited by 17
  10. 2022Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypescited by 17
  11. 2022Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognitioncited by 15
  12. 2025Post-Training Large Language Models via Reinforcement Learning from Self-Feedbackcited by 14
38 more
  1. 2024Rethinking Negative Instances for Generative Named Entity Recognitioncited by 13
  2. 2024LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertaintycited by 12
  3. 2022What do we Really Know about State of the Art NER?cited by 10
  4. 2025PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)cited by 10
  5. 2023Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learningcited by 8
  6. 2024ToNER: Type-oriented Named Entity Recognition with Generative Language Modelcited by 8
  7. 2022Zero-shot Triplet Extraction by Template Infillingcited by 7
  8. 2023E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognitioncited by 7
  9. 2023A Neural Span-Based Continual Named Entity Recognition Modelcited by 6
  10. 2023Split-NER: Named Entity Recognition via Two Question-Answering-based Classificationscited by 6
  11. 2022Span Classification with Structured Information for Disfluency Detection in Spoken Utterancescited by 5
  12. 2023Less than One-shot: Named Entity Recognition via Extremely Weak Supervisioncited by 4
  13. 2022REKnow: Enhanced Knowledge for Joint Entity and Relation Extractioncited by 3
  14. 2022DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognitioncited by 3
  15. 2023Emotion-Cause Pair Extraction as Question Answeringcited by 3
  16. 2023Span-based Named Entity Recognition by Generating and Compressing Informationcited by 3
  17. 2023A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognitioncited by 3
  18. 2023LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraintscited by 3
  19. 2024Embedded Named Entity Recognition using Probing Classifierscited by 3
  20. 2024Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?cited by 3
  21. 2024Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategycited by 3
  22. 2022Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognitioncited by 2
  23. 2022An Empirical Study on Finding Spanscited by 2
  24. 2023DMNER: Biomedical Entity Recognition by Detection and Matchingcited by 2
  25. 2024EROS: Entity-Driven Controlled Policy Document Summarizationcited by 2
  26. 2024Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity Recognitioncited by 2
  27. 2022OSLAT: Open Set Label Attention Transformer for Medical Entity Retrieval and Span Extractioncited by 1
  28. 2023Text sampling strategies for predicting missing bibliographic linkscited by 1
  29. 2023CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling approaches for NERcited by 1
  30. 2023SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extractioncited by 1
  31. 2023Comparing and combining some popular NER approaches on Biomedical taskscited by 1
  32. 2023Span Identification of Epistemic Stance-Taking in Academic Written Englishcited by 1
  33. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  34. 2023Filtered Semi-Markov CRFcited by 1
  35. 2024A Span-based Model for Extracting Overlapping PICO Entities from RCT Publicationscited by 1
  36. 2022Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRFcited by 0
  37. 2023NER-to-MRC: Named-Entity Recognition Completely Solving as Machine Reading Comprehensioncited by 0
  38. 2025Joint Automatic Speech Recognition And Structure Learning For Better Speech Understandingcited by 0

50 most cited of 55 All 55 (JSON)