The TREC 2006 question answering track contained two tasks: a main task and a complex, interactive question answering (ciQA) task. As in 2005, the main task consisted of series of factoid, list, and ``Other'' questions organized around a set of targets. The ciQA task provided a framework for participants to investigate interaction in the context of complex information needs, and was a blend of the TREC 2005 QA relationship task and the TREC 2005 HARD track. Multiple assessors judged the importance of information nuggets used to evaluate the ``Other'' responses and ciQA responses, resulting in an evaluation that is more stable and discriminative than using only a single assessor to judge nugget importance.
Citation: Special Publication (NIST SP) -
NIST Pub Series: Special Publication (NIST SP)
Pub Type: NIST Pubs
evaluation, information/knowledge management, question answering