图书馆OPAC检索中基于词典的查询意图自动识别  

Lexicon-Based Query Intent Identification for Library OPAC System

作　　者：胡伶霞[1] 

机构地区：[1]湖北工业大学工程技术学院图书馆

出　　处：《图书馆学研究》2016年第23期72-76,共5页Research on Library Science

摘　　要：图书馆书目检索中,对用户查询意图进行分析有助于提升检索的召回率和排序效果。然而,当前仅依赖用户主动反馈的方式难以获得满意的识别效果。为解决这一问题,文章提出了一种基于词典的查询意图识别策略,从实验效果看,该策略的准确率达到93.4%,远高于用户主动反馈50.6%的准确率,因此是一种有效的识别策略。Identifying users＇ query intent can help improve the recall and the effect of results ranking for library bibliographic retrieval. However, the approach which gets users＇ query intent by their initiative feedback does not perform well. To overcome this problem, this paper proposes a lexicon-based query intent identification approach. And according to the results of comparative experiments, this tactic whose precision is 93.4% performs apparently better than user initiative feedback strategy whose precision is only 50. 6%. Thus, it can be concluded that this tactic can solve query intent identification for bibliographic retrieval well.

关 键 词：OPAC 书目检索 词典 查询意图 

分 类 号：G252.7[文化科学—图书馆学]