A Deep Relevance Matching Model for Ad-hoc Retrieval
- 24 October 2016
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
Abstract
In recent years, deep neural networks have led to exciting breakthroughs in speech recognition, computer vision, and natural language processing (NLP) tasks. However, there have been few positive results of deep models on ad-hoc retrieval tasks. This is partially due to the fact that many important characteristics of the ad-hoc retrieval task have not been well addressed in deep models yet. Typically, the ad-hoc retrieval task is formalized as a matching problem between two pieces of text in existing work using deep models, and treated equivalent to many NLP tasks such as paraphrase identification, question answering and automatic conversation. However, we argue that the ad-hoc retrieval task is mainly about relevance matching while most NLP matching tasks concern semantic matching, and there are some fundamental differences between these two matching tasks. Successful relevance matching requires proper handling of the exact matching signals, query term importance, and diverse matching requirements. In this paper, we propose a novel deep relevance matching model (DRMM) for ad-hoc retrieval. Specifically, our model employs a joint deep architecture at the query term level for relevance matching. By using matching histogram mapping, a feed forward matching network, and a term gating network, we can effectively deal with the three relevance matching factors mentioned above. Experimental results on two representative benchmark collections show that our model can significantly outperform some well-known retrieval models as well as state-of-the-art deep matching models.Keywords
Funding Information
- the 973 Program of China (2014CB340401, 2013CB329606,)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (20144310, 2016102)
- The National Natural Science Foundation of China (61232010, 61472401, 61425016, 61203298)
This publication has 19 references indexed in Scilit:
- Learning to Reweight Terms with Distributed RepresentationsPublished by Association for Computing Machinery (ACM) ,2015
- MultiGranCNN: An Architecture for General Matching of Text Chunks on Multiple Levels of GranularityPublished by Association for Computational Linguistics (ACL) ,2015
- Modeling Interestingness with Deep Neural NetworksPublished by Association for Computational Linguistics (ACL) ,2014
- Glove: Global Vectors for Word RepresentationPublished by Association for Computational Linguistics (ACL) ,2014
- Learning deep structured semantic models for web search using clickthrough dataPublished by Association for Computing Machinery (ACM) ,2013
- Diagnostic Evaluation of Information Retrieval ModelsACM Transactions on Information Systems, 2011
- Efficient and effective spam filtering and re-ranking for large web datasetsInformation Retrieval Journal, 2011
- Learning to rank using gradient descentPublished by Association for Computing Machinery (ACM) ,2005
- TREC and TIPSTER experiments with inqueryInformation Processing & Management, 1995
- Learning representations by back-propagating errorsNature, 1986