计算机工程 ›› 2019, Vol. 45 ›› Issue (8): 217-223.doi: 10.19678/j.issn.1000-3428.0052473

• 人工智能及识别技术 • 上一篇    下一篇

基于规则的评价搭配抽取方法

张璞, 李逍, 刘畅   

  1. 重庆邮电大学 计算机科学与技术学院, 重庆 400065
  • 收稿日期:2018-08-27 修回日期:2018-10-10 出版日期:2019-08-15 发布日期:2019-08-08
  • 作者简介:张璞(1977-),男,副教授、博士,主研方向为文本挖掘、情感分析;李逍、刘畅,硕士研究生。
  • 基金项目:
    教育部人文社会科学研究青年基金(17YJCZH247);重庆市教委人文社会科学研究项目(17SKG055);重庆邮电大学社科基金重点项目(2018KZD06)。

Evaluation Collocation Extraction Method Based on Rules

ZHANG Pu, LI Xiao, LIU Chang   

  1. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2018-08-27 Revised:2018-10-10 Online:2019-08-15 Published:2019-08-08

摘要: 分析商品评论中评价对象和评价短语的词性和句法关系,提出一种使用规则模板进行评价搭配抽取的方法。通过词性、依存句法分析及语义依存分析结果,设计核心搭配抽取规则。引入COO算法及改进的ATT链算法,根据核心评价对象与短语的词性进一步制定识别完整评价对象与短语的规则模板,抽取评价信息。中文商品评论数据集上的实验结果表明,与最近距离方法、SBV极性传递方法和基于核心句的方法相比,该方法的F1值分别提升了43.98%、36.30%和24.83%。

关键词: 情感分析, 评价短语, 评价搭配, 依存句法分析, 语义依存分析

Abstract: This paper analyzes the part of speech and syntactic relationship between the evaluation object and the evaluation phrase in the commodity review,and proposes a method for evaluating collocation extraction using rule template.The core collocation extraction rules are designed by the results of part of speech,dependency syntactic analysis and semantic dependence analysis.The COO algorithm and the improved ATT chain algorithm are introduced,and the rule template for identifying the complete evaluation object and phrase is further developed according to the part of speech of the core evaluation object and the phrase to extract the evaluation information.Experimental results on the Chinese commodity review dataset show that compared with the nearest distance method,SBV polarity transfer method and core sentence-based method,the F1 value of the proposed method is increased by 43.98%,36.30% and 24.83% respectively.

Key words: sentiment analysis, evaluation phrase, evaluation collocation, dependency syntactic analysis, semantic dependency analysis

中图分类号: