In this paper we describe Tokyo Institute of Technology’s attempt at the TREC2007 question answering (QA) track. Keeping the same theoretical QA model as for the TREC2006 task, this year we once again focused on the factoid QA task, while investigating a new method for sentence retrieval. We deviated from our earlier approach of using web data, and instead relied solely on the supplied news wire and blog data. Our factoid and list score fell significantly from last year, while we achieved a higher other question score compared to TREC2006, using sentence retrieval rather than last year’s summarization method.
Edward W. D. Whittaker, Matthias H. Heie, Josef R.