Abstract
In this paper we suggest a QA pilot task, dubbed QolA, whose joint rationale is allow for collaboration among systems, increase multilinguality and multicollection use, and investigate ways of dealing with different strengths and weaknesses of a population of QA systems. We claim that merging answers, weighting answers, choosing among contradictory answers or generating composite answers, and verifying and validating information, by posing related questions, should be part and parcel of the question answering process. The paper motivates these ideas and suggests a way to foster research in these areas by deploying QA systems as Web services.
