Learning Query and Document Relevance from a Web-scale Click Graph
Authors:
Open Access
- 7 July 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 185-194
Abstract
Click-through logs over query-document pairs provide rich and valuable information for multiple tasks in information retrieval. This paper proposes a vector propagation algorithm on the click graph to learn vector representations for both queries and documents in the same semantic space. The proposed approach incorporates both click and content information, and the produced vector representations can directly improve ranking performance for queries and documents that have been observed in the click log. For new queries and documents that are not in the click log, we propose a two-step framework to generate the vector representation, which significantly improves the coverage of our vectors while maintaining the high quality. Experiments on Web-scale search logs from a major commercial search engine demonstrate the effectiveness and scalability of the proposed method. Evaluation results show that NDCG scores are significantly improved against multiple baselines by using the proposed method both as a ranking model and as a feature in a learning-to-rank framework.Keywords
This publication has 25 references indexed in Scilit:
- Effective query formulation with multiple information sources2012
- Exploiting site-level information to improve web search2010
- A generalized Co-HITS algorithm and its application to bipartite graphs2009
- Extracting semantic relations from query logs2007
- Random walks on the click graph2007
- Learning user interaction models for predicting web search result preferences2006
- Query expansion using random walk models2005
- Query Recommendation Using Query Logs in Search Engines2004
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- Agglomerative clustering of a search engine query log2000