Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

被引:63
作者
Fan, Yixing [1 ,2 ]
Guo, Jiafeng [1 ,2 ]
Lan, Yanyan [1 ,2 ]
Xu, Jun [1 ,2 ]
Zhai, Chengxiang [3 ]
Cheng, Xueqi [1 ,2 ]
机构
[1] Univ Chinese Acad Sci, Beijing, Peoples R China
[2] Chinese Acad Sci, CAS Key Lab Network Data Sci & Technol, Inst Comp Technol, Beijing, Peoples R China
[3] Univ Illinois, Dept Comp Sci, 1304 W Springfield Ave, Urbana, IL 61801 USA
来源
ACM/SIGIR PROCEEDINGS 2018 | 2018年
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
relevance patterns; ad-hoc retrieval; neural network;
D O I
10.1145/3209978.3209980
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Assessing relevance between a query and a document is challenging in ad-hoc retrieval due to its diverse patterns, i.e., a document could be relevant to a query as a whole or partially as long as it provides sufficient information for users' need. Such diverse relevance patterns require an ideal retrieval model to be able to assess relevance in the right granularity adaptively. Unfortunately, most existing retrieval models compute relevance at a single granularity, either document-wide or passage-level, or use fixed combination strategy, restricting their ability in capturing diverse relevance patterns. In this work, we propose a data-driven method to allow relevance signals at different granularities to compete with each other for final relevance assessment. Specifically, we propose a HIerarchical Neural maTching model (HiNT) which consists of two stacked components, namely local matching layer and global decision layer. The local matching layer focuses on producing a set of local relevance signals by modeling the semantic matching between a query and each passage of a document. The global decision layer accumulates local signals into different granularities and allows them to compete with each other to decide the final relevance score. Experimental results demonstrate that our HiNT model outperforms existing state-of-the-art retrieval models significantly on benchmark ad-hoc retrieval datasets.
引用
收藏
页码:375 / 384
页数:10
相关论文
共 39 条
  • [1] Probabilistic models of information retrieval based on measuring the divergence from randomness
    Amati, G
    Van Rijsbergen, CJ
    [J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2002, 20 (04) : 357 - 389
  • [2] [Anonymous], 2017, ARXIV170501509
  • [3] [Anonymous], 2003, Journal of machine learning research
  • [4] [Anonymous], 2008, Advances in neural information processing systems, DOI DOI 10.1007/978-1-4471-4072-6_12
  • [5] Bendersky M, 2008, LECT NOTES COMPUT SC, V4956, P162
  • [6] Burges C. J., 2010, Learning, V11, DOI DOI 10.1111/J.1467-8535
  • [7] Callan J. P., 1994, SIGIR '94. Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, P302
  • [8] TREC AND TIPSTER EXPERIMENTS WITH INQUERY
    CALLAN, JP
    CROFT, WB
    BROGLIO, J
    [J]. INFORMATION PROCESSING & MANAGEMENT, 1995, 31 (03) : 327 - 343
  • [9] Chengxiang Zhai, 2001, SIGIR Forum, P334
  • [10] Clarke C L, 2005, TREC