Skip to main navigation Skip to search Skip to main content

Paraphrase based similar expression generation

  • Wei He*
  • , Zhanyi Liu
  • , Ting Liu
  • *Corresponding author for this work
  • Harbin Institute of Technology

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

Abstract

In this paper we propose a novel paraphrase based method to improve the performance of the similar expressions generation that has been widely used in writing assistant system. The users' queries are paraphrased to multiple expressions which cover abundant example sentences in the system. Three paraphrase methods are presented to satisfy the users' different intentions. First of all, we employ a statistical collocation model to generate collocations for two-word queries. Then we use a phrase based paraphrase model and a dependency based paraphrase model to substitute contiguous phrases and long-distance collocations in multi-word queries (> 2 words). The experimental results indicate that the proposed method can effectively help the users to correct their inappropriate expressions.

Original languageEnglish
Title of host publicationIntelligence Computation and Evolutionary Computation - Results of 2012 International Conference of Intelligence Computation and Evolutionary Computation, ICEC 2012
PublisherSpringer Verlag
Pages369-374
Number of pages6
ISBN (Print)9783642316555
DOIs
StatePublished - 2013
Event2012 International Conference of Intelligence Computation and Evolutionary Computation, ICEC 2012 - Wuhan, China
Duration: 7 Jul 20127 Jul 2012

Publication series

NameAdvances in Intelligent Systems and Computing
Volume180 AISC
ISSN (Print)2194-5357

Conference

Conference2012 International Conference of Intelligence Computation and Evolutionary Computation, ICEC 2012
Country/TerritoryChina
CityWuhan
Period7/07/127/07/12

Keywords

  • Paraphrase
  • Sentence Retrieval
  • Similar Expression

Fingerprint

Dive into the research topics of 'Paraphrase based similar expression generation'. Together they form a unique fingerprint.

Cite this