Abstract:

One of the limitations of semantic parsing approaches to open-domain question answering is the lexicosyntactic gap between natural language questions and knowledge base entries — there are many ways to ask a question, all with the same answer. In this paper we propose to bridge this gap by generating paraphrases to the input question with the goal that at least one of them will be correctly mapped to a correct knowledge-base query. We introduce a novel grammar model for paraphrase generation that does not require any sentence-aligned paraphrase corpus. Our key idea is to leverage the flexibility and scalability of latent-variable probabilistic context-free grammars to sample paraphrases. We do an extrinsic evaluation of our paraphrases by plugging them into a semantic parser for Freebase. Our evaluation experiments on WebQuestions benchmark dataset show that the performance of the semantic parser significantly improves over strong
baselines.

Bio:

Shashi Narayan is a research associate at School of Informatics at the University of Edinburgh. He is currently working with Shay Cohen onthe problems of spectral methods for parsing and generation. Before,he earned his doctoral degree in 2014 from Université de Lorraine,under the supervision of Claire Gardent. He received Erasmus MundusMasters scholarship (2009-2011) in Language and CommunicationTechnology (EM-LCT). He did his major in Computer Science and Engineeringfrom Indian Institute of Technology (IIT), Kharagpur India. He is interested in the application of syntax and semantics to solvevarious NLP problems, in particular, natural language generation,parsing, sentence simplification, paraphrase generation and questionanswering.