mlsanityData to 7 Oct 2026

Boundary Smoothing for Named Entity Recognition

arXiv 2204.12031 ↗First posted 26 Apr 2022cs.CL cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

28 of 51 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2018Deep contextualized word representationscited by 2,285
  7. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  8. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  9. 2019When Does Label Smoothing Help?cited by 985
  10. 2016Neural Architectures for Named Entity Recognitioncited by 548
  11. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 544
  12. 2019Fantastic Generalization Measures and Where to Find Themcited by 507
16 more
  1. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  2. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 262
  3. 2020Does label smoothing mitigate label noise?cited by 204
  4. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
  5. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  6. 2020Named Entity Recognition as Dependency Parsingcited by 150
  7. 2019Span-based Joint Entity and Relation Extraction with Transformer Pre-trainingcited by 132
  8. 2016Towards better decoding and language model integration in sequence to sequence modelscited by 100
  9. 2018Chinese NER Using Lattice LSTMcited by 81
  10. 2020FLAT: Chinese NER Using Flat-Lattice Transformercited by 67
  11. 2019CrossWeigh: Training Named Entity Tagger from Imperfect Annotationscited by 60
  12. 2021Locate and Label: A Two-stage Identifier for Nested Named Entity Recognitioncited by 60
  13. 2019Neural Architectures for Nested NER through Linearizationcited by 56
  14. 2021A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognitioncited by 33
  15. 2019Simplify the Usage of Lexicon in Chinese NERcited by 23
  16. 2021MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognitioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 10; 2024: 1; 2025: 1; 2026: 1.

21 papers.

Sort:

By area:

  1. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  2. 2023PromptNER: Prompt Locating and Typing for Named Entity Recognitioncited by 17
  3. 2023mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learningcited by 14
  4. 2023A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NERcited by 9
  5. 2022An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognitioncited by 7
  6. 2022PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Taskscited by 7
  7. 2023E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognitioncited by 7
  8. 2023FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extractioncited by 7
  9. 2023Split-NER: Named Entity Recognition via Two Question-Answering-based Classificationscited by 6
  10. 2023DiffusionNER: Boundary Diffusion for Named Entity Recognitioncited by 5
  11. 2022Deep Span Representations for Named Entity Recognitioncited by 4
  12. 2022Rethinking Label Smoothing on Multi-hop Question Answeringcited by 4
9 more
  1. 2022Recognizing Nested Entities from Flat Supervision: A New NER Subtask, Feasibility and Challengescited by 2
  2. 2022TERMinator: A system for scientific texts processingcited by 1
  3. 2023Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsingcited by 1
  4. 2024A Span-based Model for Extracting Overlapping PICO Entities from RCT Publicationscited by 1
  5. 2022End-to-End Entity Detection with Proposer and Regressorcited by 0
  6. 2022MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languagescited by 0
  7. 2023Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classificationcited by 0
  8. 2025Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotationscited by 0
  9. 2026Mitigating Entity Type Confusion in Cross-Domain NER via Multidimensional Quantification and Reasoning Enhancementcited by 0