Linear Co-occurrence Rate Networks (L-CRNs) for Sequence Labeling

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
8 Downloads (Pure)

Abstract

Sequence labeling has wide applications in natural language processing and speech processing. Popular sequence labeling models suffer from some known problems. Hidden Markov models (HMMs) are generative models and they cannot encode transition features; Conditional Markov models (CMMs) suffer from the label bias problem; And training of conditional random fields (CRFs) can be expensive. In this paper, we propose Linear Co-occurrence Rate Networks (L-CRNs) for sequence labeling which avoid the mentioned problems with existing models. The factors of L-CRNs can be locally normalized and trained separately, which leads to a simple and efficient training method. Experimental results on real-world natural language processing data sets show that L-CRNs reduce the training time by orders of magnitudes while achieve very competitive results to CRFs.
Original languageUndefined
Title of host publicationProceedings of the Second International Conference on Statistical Language and Speech Processing, SLSP 2014
Place of PublicationBerlin
PublisherSpringer
Pages185-196
Number of pages12
ISBN (Print)978-3-319-11396-8
DOIs
Publication statusPublished - Oct 2014

Publication series

NameLecture Notes in Artifical Intelligence
PublisherSpringer Verlag
Volume8791
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Keywords

  • EWI-25353
  • DB-DM: DATA MINING
  • HMMs
  • METIS-309684
  • CRFs
  • IR-93325
  • Co-occurrence rate
  • Sequence labeling

Cite this

Zhu, Z., Hiemstra, D., & Apers, P. M. G. (2014). Linear Co-occurrence Rate Networks (L-CRNs) for Sequence Labeling. In Proceedings of the Second International Conference on Statistical Language and Speech Processing, SLSP 2014 (pp. 185-196). (Lecture Notes in Artifical Intelligence; Vol. 8791). Berlin: Springer. https://doi.org/10.1007/978-3-319-11397-5_14