More than relevance

• DOI: 10.1145/2396761.2398523
• Publication Date: 2012-11-15T16:38:00Z
• Authors: Xiaofei Zhu; Jiafeng Guo; Xueqi Cheng; Yanyan Lan
• Keywords: Relevance; Information needs; Spatial Query; Relevance Feedback

Query recommendation plays a critical role in helping users' search. Most existing approaches on query aim to recommend relevant queries. However, the ultimate goal of is assist users reformulate queries so that they can accomplish their search task successfully and quickly. Only considering relevance apparently not directly toward this goal. In paper, we argue it more important with high utility, i.e., better satisfy information needs. For purpose, propose novel generative model, referred as Utility Model (QUM), capture utility by simultaneously modeling reformulation click behaviors. The experimental results publicly released log show that, our approach effective find thus satisfying