Skip to main navigation Skip to search Skip to main content

SLDP: Sequence learning dependency parsing model using long short-term memory

  • School of Computer Science and Technology, Harbin Institute of Technology

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

Abstract

Recent work on neural network models shows success in dependency parsing. In this paper, we present a sequence learning dependency parsing (SLDP) model using long short-term memory for shift-reduce parser. A feed-forward neural network is used to build greedy model from rich local features. With the features extracted by the local model, we further train a long short-term memory (LSTM) model optimized for global parsing sequences. Our model has the capability of learning not only atomic feature combinations automatically but also the long distance dependent information for dependency parsing. Experiments on English Penn Treebank show that our SLDP model significantly outperforms the baseline, achieving 90.7% unlabeled attachment score and 89.0% labeled attachment score.

Original languageEnglish
Title of host publicationProceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016
PublisherIEEE Computer Society
Pages111-116
Number of pages6
ISBN (Electronic)9781509003891
DOIs
StatePublished - 2 Jul 2016
Externally publishedYes
Event2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016 - Jeju Island, Korea, Republic of
Duration: 10 Jul 201613 Jul 2016

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume1
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016
Country/TerritoryKorea, Republic of
CityJeju Island
Period10/07/1613/07/16

Keywords

  • Dependency parsing
  • Long short-term memory
  • Natural language processing
  • Neural networks
  • Syntactic parsing

Fingerprint

Dive into the research topics of 'SLDP: Sequence learning dependency parsing model using long short-term memory'. Together they form a unique fingerprint.

Cite this