# Hybrid semi-Markov CRF for Neural Sequence Labeling

arXiv: https://arxiv.org/abs/1805.03838 · HTML: https://mlsanity.com/paper/1805.03838/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2018.

## Built on by (most cited first, 9 of 9)

- [WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition](https://mlsanity.com/paper/2212.03506/) (2022)
- [kNN-NER: Named Entity Recognition with Nearest Neighbor Search](https://mlsanity.com/paper/2203.17103/) (2022)
- [Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-stage Span Labeling](https://mlsanity.com/paper/2112.09488/) (2021)
- [Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting](https://mlsanity.com/paper/2204.11406/) (2022)
- [Joint Span Segmentation and Rhetorical Role Labeling with Data Augmentation for Legal Documents](https://mlsanity.com/paper/2302.06448/) (2023)
- [USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER](https://mlsanity.com/paper/2305.02517/) (2023)
- [Filtered Semi-Markov CRF](https://mlsanity.com/paper/2311.18028/) (2023)
- [Exploiting Global Contextual Information for Document-level Named Entity Recognition](https://mlsanity.com/paper/2106.00887/) (2021)
- [Streaming Structured Inference with Flash-SemiCRF](https://mlsanity.com/paper/2604.18780/) (2026)

## Abstract (arXiv)

This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for the tasks of assigning labels to segments by extracting features from and describing transitions between segments instead of words. In this paper, we improve the existing SCRF methods by employing word-level and segment-level information simultaneously. First, word-level labels are utilized to derive the segment scores in SCRFs. Second, a CRF output layer and an SCRF output layer are integrated into an unified neural network and trained jointly. Experimental results on CoNLL 2003 named entity recognition (NER) shared task show that our model achieves state-of-the-art performance when no external knowledge is used.