Skip to main navigation Skip to search Skip to main content

An improved sentence polishing model used in automatic extraction

  • Yan Wu*
  • , Xiukun Li
  • , Ruifeng Xu
  • , Lin Yao
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • School of Computer Science and Technology, Harbin Institute of Technology

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

Abstract

Language modeling plays a critical role for automatic extraction. Typically, the statistical model of automatic extraction suffers from the lack of the subject semantic consistency between sentences and the redundancy of information. In this study, we first introduce our work on automatic extraction, and then analyze the disadvantages of different extracting models. We then present a advanced mathematical model to overcome these lacks based on computational linguistics. As shown by experiments, the proposed modeling and methods can significantly reduce the redundancy of information and increase the subject semantic consistency between sentences of automatic abstraction with moderate computational cost.

Original languageEnglish
Title of host publicationProceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011
PublisherIEEE Computer Society
Pages1884-1888
Number of pages5
ISBN (Print)9781457703065
DOIs
StatePublished - 2011
Externally publishedYes
Event10th International Conference on Machine Learning and Cybernetics, ICMLC 2011 - Guilin, Guangxi, China
Duration: 10 Jul 201113 Jul 2011

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume4
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference10th International Conference on Machine Learning and Cybernetics, ICMLC 2011
Country/TerritoryChina
CityGuilin, Guangxi
Period10/07/1113/07/11

Keywords

  • Automatic abstraction
  • automatic extraction
  • language modeling
  • semantic paragraph
  • text representation

Fingerprint

Dive into the research topics of 'An improved sentence polishing model used in automatic extraction'. Together they form a unique fingerprint.

Cite this