QRU-1: A Public Dataset for Promoting Query Representation and Understanding Research

1. INTRODUCTION Understanding the user’s intent or the information need that underlies a query has long been recognized as a crucial part of effective information retrieval. With the recent availability of large amounts of data about user behavior and queries in web search logs, there has been an upsurge of interest in new approaches to query understanding and representing user intent. In order to promote discussion of these approaches and to identify challenges and long term research goals, we organized a series of two workshops on Query Representation and Understanding at SIGIR 2010 and SIGIR 2011 [2]. The readers may refer to the workshop website1 for more detailed information about these workshops. A key issue, raised by many workshop participants, was the importance of creating public datasets for query representation and understanding research. There are two main ob1 Workshop on Web Search Click Data, February 12, 2012, Seattle, Wash