mlsanityData to 7 Oct 2026

Masked Conditional Random Fields for Sequence Labeling

arXiv 2103.10682 ↗First posted 19 Mar 2021cs.LG cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Conditional Random Field (CRF) based neural models are among the most performant methods for solving sequence labeling problems. Despite its great success, CRF has the shortcoming of occasionally generating illegal sequences of tags, e.g. sequences containing an "I-" tag immediately after an "O" tag, which is forbidden by the underlying BIO tagging scheme. In this work, we propose Masked Conditional Random Field (MCRF), an easy to implement variant of CRF that impose restrictions on candidate paths during both training and decoding phases. We show that the proposed method thoroughly resolves this issue and brings consistent improvement over existing CRF-based models with near zero additional cost.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

17 of 32 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018Deep contextualized word representationscited by 2,285
  3. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 544
  4. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  5. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  6. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  7. 2019Dice Loss for Data-imbalanced NLP Taskscited by 180
  8. 2017Semi-supervised sequence tagging with bidirectional language modelscited by 86
  9. 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
  10. 2018Chinese NER Using Lattice LSTMcited by 81
  11. 2018Joint Slot Filling and Intent Detection via Capsule Neural Networkscited by 73
  12. 2020FLAT: Chinese NER Using Flat-Lattice Transformercited by 67
5 more
  1. 2019Glyce: Glyph-vectors for Chinese Character Representationscited by 46
  2. 2020Torch-Struct: Deep Structured Prediction Librarycited by 40
  3. 2019Simplify the Usage of Lexicon in Chinese NERcited by 23
  4. 2019GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labelingcited by 22
  5. 2018Unsupervised Transfer Learning for Spoken Language Understanding in Intelligent Agentscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 1; 2024: 0; 2025: 1; 2026: 1.

6 papers.

  1. 2021Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extractioncited by 11
  2. 2023A unified front-end framework for English text-to-speech synthesiscited by 4
  3. 2025Logits-Constrained Framework with RoBERTa for Ancient Chinese NERcited by 1
  4. 2021Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Applicationcited by 0
  5. 2022Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Datacited by 0
  6. 2026PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectoriescited by 0