This paper presents a syntax-driven ap- proach to question answering, specifically the answer-sentence selection problem for short-answer questions. Rather than us- ing syntactic features to augment exist- ing statistical classifiers (as in previous work), we build on the idea that ques- tions and their (correct) answers relate to each other via loose but predictable syntac- tic transformations. We propose a prob- abilistic quasi-synchronous grammar, in- spired by one proposed for machine trans- lation (D. Smith and Eisner, 2006), and pa- rameterized by mixtures of a robust non- lexical syntax/alignment model with a(n optional)lexical-semantics-drivenlog-linear model. Our model learns soft alignments as a hidden variable in discriminative training. ExperimentalresultsusingtheTRECdataset ar...

Click Here to View the Paper In XML Format