A Cyclic Cascaded CRFs Model for Opinion Targets Identification Based on Rules and Statistics - Intelligent Information Processing VIII Access content directly
Conference Papers Year : 2016

A Cyclic Cascaded CRFs Model for Opinion Targets Identification Based on Rules and Statistics

Hengxun Li
  • Function : Author
  • PersonId : 1020682
Chun Liao
  • Function : Author
  • PersonId : 1020683
Guangjun Hu
  • Function : Author
  • PersonId : 1020684
Ning Wang
  • Function : Author
  • PersonId : 1020685

Abstract

Opinion sentences on e-commerce platform, microblog and forum contain lots of emotional information. And opinion targets identification plays an import role in huge potential commercial value mining, especially in sales decision making and development trend forecasting. Traditional CRFs-based method has achieved a pretty good result to a certain extent. However, its discovery ability of out-of-vocabulary words and optimization of the mining model are both insufficient. We propose a novel cyclic cascaded CRFs model for opinion targets identification which incorporates rule-based and statistic-based methods. The approach acquires candidate opinion targets through part-of-speech, syntactic and semantic rules, and integrates them in a cyclic cascaded CRFs model for the accurate opinion targets identification. Experimental results on COAE2014 dataset show the outperformance of this method.
Fichier principal
Vignette du fichier
433802_1_En_27_Chapter.pdf (491.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01614995 , version 1 (11-10-2017)

Licence

Attribution

Identifiers

Cite

Hengxun Li, Chun Liao, Guangjun Hu, Ning Wang. A Cyclic Cascaded CRFs Model for Opinion Targets Identification Based on Rules and Statistics. 9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. pp.267-275, ⟨10.1007/978-3-319-48390-0_27⟩. ⟨hal-01614995⟩
218 View
78 Download

Altmetric

Share

Gmail Facebook X LinkedIn More