Harnessing Semantics for Answer Sentence Retrieval

Abstract

Finding answer passages from the Web is a challenging task. One major difficulty is to retrieve sentences that may not have many terms in common with the question. In this paper, we experiment with two semantic approaches for finding non-factoid answers using a learning-to-rank retrieval setting. We show that using semantic representations learned from external resources such as Wikipedia or Google News may substantially improve the quality of top-ranked retrieved answers.