English

Neural CRF transducers for sequence labeling

Machine Learning 2018-11-06 v1 Computation and Language Machine Learning

Abstract

Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to implement the non-linear node potentials in CRFs, but still keeping the linear-chain hidden structure. In this paper, we propose NCRF transducers, which consists of two RNNs, one extracting features from observations and the other capturing (theoretically infinite) long-range dependencies between labels. Different sequence labeling methods are evaluated over POS tagging, chunking and NER (English, Dutch). Experiment results show that NCRF transducers achieve consistent improvements over linear-chain NCRFs and RNN transducers across all the four tasks, and can improve state-of-the-art results.

Keywords

Cite

@article{arxiv.1811.01382,
  title  = {Neural CRF transducers for sequence labeling},
  author = {Kai Hu and Zhijian Ou and Min Hu and Junlan Feng},
  journal= {arXiv preprint arXiv:1811.01382},
  year   = {2018}
}
R2 v1 2026-06-23T05:03:31.102Z