计算机科学 ›› 2015, Vol. 42 ›› Issue (5): 98-105.doi: 10.11896/j.issn.1002-137X.2015.05.020

• • 上一篇    下一篇

基于知识图的观点句识别算法研究

程显毅,刘 颖   

  1. 南通大学计算机科学与技术学院 南通226019,江苏大学计算机科学与通信工程学院 镇江212013
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(61340037,61171132)资助

Research on Algorithm of Perspective Sentence Identification Based on Knowledge Map

CHENG Xian-yi and LIU Ying   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对观点句的特点提出了适合观点句识别的特征抽取规则。在此基础上,融合图论中最小割原理和机器学习分类方法,引入知识图的概念,并提出了基于知识图的观点句识别算法。以公开评测语料、自建语料和开放语料进行了相关实验,结果表明:基于知识图的观点句识别算法的分类性能和稳定性有明显优势。

Abstract: Aiming at the characteristics of the perspective sentence,knowledge rule was proposed that is suitable for perspective sentence identification.On this basis,we mixed the minimum cut principle of graph theory with machine learning classification method,introduced the concept of knowledge map,and proposed a algorithm of sentence recognition based on the knowledge map.In public evaluation corpus,self-builted corpora and open corpus,we conducted related experiment and the experimental results show that the perspective sentence classification performance and stability of the recognitioned algorithm based on the knowledge map have obvious advantages.

[1] 孟小峰,慈祥.大数据管理:概念、技术与挑战[J].计算机研究与发展,2013,0(1):146-163
[2] Seki Y,et al.Overview of multilingual opinion analysis task at NTCIR-7[C]∥Proeeedings of NTCIR-7 Workshop Meeting.Tokyo,Japan,2008:185-203
[3] 王昕.多粒度融合的汉语句子主观性和情感分类方法研究[D].哈尔滨:黑龙江大学,2011
[4] Riloff E,Wiebe J,Phillips W.Exploiting subjectivity classification to improve information extraction[C]∥Proceedings of AAAI’05.2005:1106-1111
[5] Wiebe J,Mihaleea R.Word sense and subjectivity[C]∥Procee-dings of ACL/COLING’06.Sydney,Australia,2006:1065-1072
[6] Mihalcea R,Banea C,Wiebe J.Learning Multilingual Subjective Language via Cross-Lingual Projections[C]∥Proceedings of the Association for Computational Linguistics (ACL2007).Prague,June 2007:1013-1019
[7] Jindal N,Liu Bing.Identifying Comparative Sentences in Text documents[C]∥Proceedings of SIGIR’06.Seattle,Washington,USA,2006:244-251
[8] Yu Hong,Hatzivassiloglou V.Towards answering opinion questions:Separating facts from opinions and identifying the polarity of opinion sentences[C]∥Proceedings of EMNLP’03.2003:129-136
[9] Pang Bo,Lee L.A Sentimental education:sentiment analysisusing subjectivity summariza tion based on minimum cuts[C]∥Proceedings of ACL’04.Bareelona,SPain,2004:271-278
[10] 叶强,张紫琼,罗振雄.面向互联网评论情感分析的中文主观性自动判别方法研究[J].系统信息学报,2007,1(1):79-91
[11] Jijkoun V,de Rjike M,Wouter W.Generating focused topic-specific Sentim ent lexicons[C]∥Proceedings of ACL2010.2010:585-594
[12] Zhao W X,Jiang Jing,et al.Jointly modeling aspects and opi-nions with aMaxEnt-LDA hybrid[C]∥Proceedings of EMNLP2010.2010:56-65
[13] 中国计算机协会.中文微博情感分析评测结果[EB/OL].http://tcci.ccf.org.cn/ conference/2012/ pages/page04_ evares.html

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!