# Masked Conditional Random Fields for Sequence Labeling

arXiv: https://arxiv.org/abs/2103.10682 · HTML: https://mlsanity.com/paper/2103.10682/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [Semi-supervised sequence tagging with bidirectional language models](https://mlsanity.com/paper/1705.00108/) (2017)
- [A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1907.00390/) (2019)
- [Chinese NER Using Lattice LSTM](https://mlsanity.com/paper/1805.02023/) (2018)
- [Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1812.09471/) (2018)
- [FLAT: Chinese NER Using Flat-Lattice Transformer](https://mlsanity.com/paper/2004.11795/) (2020)
- [Glyce: Glyph-vectors for Chinese Character Representations](https://mlsanity.com/paper/1901.10125/) (2019)
- [Torch-Struct: Deep Structured Prediction Library](https://mlsanity.com/paper/2002.00876/) (2020)
- [Simplify the Usage of Lexicon in Chinese NER](https://mlsanity.com/paper/1908.05969/) (2019)
- [GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling](https://mlsanity.com/paper/1906.02437/) (2019)
- [Unsupervised Transfer Learning for Spoken Language Understanding in Intelligent Agents](https://mlsanity.com/paper/1811.05370/) (2018)

## Built on by (most cited first, 6 of 6)

- [Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction](https://mlsanity.com/paper/2112.10424/) (2021)
- [A unified front-end framework for English text-to-speech synthesis](https://mlsanity.com/paper/2305.10666/) (2023)
- [Logits-Constrained Framework with RoBERTa for Ancient Chinese NER](https://mlsanity.com/paper/2505.02983/) (2025)
- [Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application](https://mlsanity.com/paper/2111.09078/) (2021)
- [Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data](https://mlsanity.com/paper/2210.17122/) (2022)
- [PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectories](https://mlsanity.com/paper/2602.12080/) (2026)

## 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.