Semantic composition of distributed representations for query subtopic mining

Semantic composition of distributed representations for query subtopic mining
复制标题

用于查询子主题挖掘的分布式表示的语义组合

DOI:
10.1631/fitee.1601476
复制
发表时间:
2018-11
影响因子:
3
通讯作者:
Lizhen Liu
Lizhen Liu
中科院分区:
工程技术3区
文献类型:
--
作者:
Wei Song;Ying Liu;Lizhen Liu

文献摘要

参考文献

相似文献

在信息检索任务中,查询意图的推断具有重要意义.查询子主题挖掘的目的是为给定的查询找到可能的子主题来表示潜在的意图。由于短查询的性质,子主题挖掘具有挑战性。近年来,分布式词语表示或词语序列学习得到了迅速发展,并对许多领域产生了重大影响。目前还不清楚分布式表示是否能有效地缓解查询子主题挖掘的挑战。在本文中,我们利用和比较的主要语义组成的分布式表示查询子主题挖掘。具体来说,我们专注于两种类型的分布式表示:段落向量,直接表示具有任意长度的单词序列,和单词向量组合。我们彻底调查的语义组合策略和学习分布式表示的数据类型的影响。实验是在国家信息学试验台和信息访问研究社区研究所提供的公共数据集上进行的。实验结果表明,与传统的语义表示方法相比,分布式语义表示方法在查询子主题挖掘中具有优异的性能。更多的见解也被报道。
Inferring query intent is significant in information retrieval tasks. Query subtopic mining aims to find possible subtopics for a given query to represent potential intents. Subtopic mining is challenging due to the nature of short queries. Learning distributed representations or sequences of words has been developed recently and quickly, making great impacts on many fields. It is still not clear whether distributed representations are effective in alleviating the challenges of query subtopic mining. In this paper, we exploit and compare the main semantic composition of distributed representations for query subtopic mining. Specifically, we focus on two types of distributed representations: paragraph vector which represents word sequences with an arbitrary length directly, and word vector composition. We thoroughly investigate the impacts of semantic composition strategies and the types of data for learning distributed representations. Experiments were conducted on a public dataset offered by the National Institute of Informatics Testbeds and Community for Information Access Research. The empirical results show that distributed semantic representations can achieve outstanding performance for query subtopic mining, compared with traditional semantic representations. More insights are reported as well.
DOI: --
发表时间: 2013
期刊: --
影响因子: --
作者:
T. Sakai;Zhicheng Dou;Takehiro Yamamoto;Yiqun Liu;Min Zhang;Ruihua Song
通讯作者: T. Sakai;Zhicheng Dou;Takehiro Yamamoto;Yiqun Liu;Min Zhang;Ruihua Song
DOI: --
发表时间: 2010-08
期刊: --
影响因子: --
作者:
Fabio Massimo Zanzotto;Ioannis Korkontzelos;Francesca Fallucchi;S. Manandhar
通讯作者: Fabio Massimo Zanzotto;Ioannis Korkontzelos;Francesca Fallucchi;S. Manandhar
DOI: --
发表时间: 2011
期刊: --
影响因子: --
作者:
Xue Jiang;Xianpei Han;Le Sun-
通讯作者: Xue Jiang;Xianpei Han;Le Sun-
DOI: 10.1145/1772690.1772780
发表时间: 2010-04
影响因子: 4.5
作者:
Rodrygo L. T. Santos;Craig Macdonald;I. Ounis
通讯作者: Rodrygo L. T. Santos;Craig Macdonald;I. Ounis
DOI: 10.1145/1526709.1526773
发表时间: 2009-04
期刊: --
影响因子: --
作者:
Jian Hu;G. Wang;F. Lochovsky;Jian-Tao Sun-;Zheng Chen
通讯作者: Jian Hu;G. Wang;F. Lochovsky;Jian-Tao Sun-;Zheng Chen