Paper: Paraphrase-Driven Learning for Open Question Answering

ACL ID P13-1158
Title Paraphrase-Driven Learning for Open Question Answering
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2013
Authors

We study question answering as a ma- chine learning problem, and induce a func- tion that maps open-domain questions to queries over a database of web extrac- tions. Given a large, community-authored, question-paraphrase corpus, we demon- strate that it is possible to learn a se- mantic lexicon and linear ranking func- tion without manually annotating ques- tions. Our approach automatically gener- alizes a seed lexicon and includes a scal- able, parallelized perceptron parameter es- timation scheme. Experiments show that our approach more than quadruples the re- call of the seed lexicon, with only an 8% loss in precision.