Abstract

We describe recent extensions to the Ephyra question answering (QA) system and their evaluation in the TREC 2007 QA track. Existing syntactic answer extraction approaches for factoid and list questions have been complemented with a high-accuracy semantic approach that generates a semantic representation of the question and extracts answer candidates from similar semantic structures in the corpus. Candidates found by different answer extractors are combined and ranked by a statistical framework that integrates a variety of answer validation techniques and similarity measures to estimate a probability for each candidate. A novel answer type classifier combines a statistical model and hand-coded rules to predict the answer type based on syntactic and semantic features of the question. Our approach for the ‘other ’ questions uses Wikipedia and Google to judge the relevance of answer candidates found in the corpora. 1.

Citations