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.
出处
《图书馆学研究》
CSSCI
2016年第23期72-76,共5页
Research on Library Science
关键词
OPAC
书目检索
词典
查询意图
OPAC
bibliographic retrieval
lexicon
query intent
