Edinburgh Research Explorer

Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationProceedings of The 9th International Natural Language Generation conference
Place of PublicationEdinburgh, UK
PublisherAssociation for Computational Linguistics
Pages153–162
Number of pages10
DOIs
Publication statusPublished - 8 Sep 2016
Event9th International Natural Language Generation conference - Edinburgh, United Kingdom
Duration: 5 Sep 20168 Sep 2016
http://www.macs.hw.ac.uk/InteractionLab/INLG2016/

Conference

Conference9th International Natural Language Generation conference
Abbreviated titleINLG 2016
CountryUnited Kingdom
CityEdinburgh
Period5/09/168/09/16
Internet address

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.

Event

9th International Natural Language Generation conference

5/09/168/09/16

Edinburgh, United Kingdom

Event: Conference

Download statistics

No data available

ID: 28391090