Paper Info
Title
KB-Enabled Query Recommendation for Long-Tail Queries
Abstract
In recent years, query recommendation algorithms have been designed to provide related queries for search engine users. Most of these solutions, which perform extensive analysis of users' search history (or query logs), are largely insufficient for long-tail queries that rarely appear in query logs. To handle such queries, we study a new solution, which makes use of a knowledge base (or KB), such as YAGO and Freebase. A KB is a rich information source that describes how real-world entities are connected. We extract entities from a query, and use these entities to explore new ones in the KB. Those discovered entities are then used to suggest new queries to the user. As shown in our experiments, this approach provides better recommendation results for long-tail queries than existing solutions. We have also incorporated caching to improve the efficiency of our solutions; experimentally, query suggestion can be completed within 100ms. We further propose a framework that integrates our solution with existing query recommendation algorithms. This solution provides the best recommendation results for any query, regardless of whether it is a long-tail query or not. Due to its high performance and efficiency, the solution can support online query recommendation.
Year
DOI
Venue
2016
10.1145/2983323.2983650
ACM International Conference on Information and Knowledge Management
Keywords
Field
DocType
query recommendation,knowledge base,Web search,query log mining
Query optimization,Web search query,Data mining,RDF query language,Query language,Information retrieval,Query expansion,Computer science,Sargable,Web query classification,Spatial query
Conference
Citations 
PageRank 
References 
7
0.46
22
Authors
4
Name
Order
Citations
PageRank
Zhipeng Huang1886.16
Bogdan Cautis224623.35
Reynold Cheng33069154.13
Yudian Zheng441816.91