SIGIR 2011 Workshop on "entertain me"

Supporting Complex Search Tasks

28 July 2011
Workshop Homepage Presentations Call for Participation Organizers


There is a striking difference in how we ask another (unknown) person for information, giving a lot of context information and very precisely articulating what we want and why, and how we communicate with current search engines, typically with a series of short queries. Can't we do better? Think about a novel information access tool that actively supports a searcher to articulate a whole search task, and to interactively explore the results of every stage of the process. That is, can we support the entire search episode?

The leading example will be ourselves at the last day of SIGIR 2011 in Beijing, in a city we don't know, trying to plan our post-workshop evening (locating suitable restaurants/theaters/clubs, looking at reviews, locations and distances, individual preferences, time-tables, etc.). This could be formulated as a highly complex query or search strategy, that could be interactively constructed based on an initial plan and further feedback. Eliciting such a query from a searcher would require complex interaction, and an expressive query language combining several constraints on content as well as on structure (i.e. collection structure and annotation). However, the most natural query for this is in fact dead simple: entertain me. That is, the most natural way to express this highly complex information need is utterly simplistic, and all the other needed information could be filled in from implicit and explicit contextual information on the specific search request, the specific location/time/IP, the searcher and her preferences, etc.

The overall goal of the workshop can be succinctly summarized as to make IR systems support searchers during their entire search episodes when interactively solving a complex task, such as the entertain me planning problem. Although a SIGIR Workshop devoted to a single query may seem extravagant, this query is just one example of the general problem of supporting simple and common requests that express complex and dynamic needs.

We aim to bring together a varied group of researchers covering both user and system centered approaches, and together work on the problem and potential solutions, and identify the barriers to success and work on ways of addressing them.

We envision a lively and interactive workshop, with the explicit aim to push the boundaries and think outside the box.



This workshop will be held as part of the 34th Annual International ACM SIGIR Conference on Research & Development on Information Retrieval, Beijing, 2011. Information on Beijing can be found in the Wikipedia.