Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing
This addresses a key bottleneck in semantic parsing for question answering, though it is an incremental advance in paraphrase generation methods.
The paper tackles the lexicosyntactic gap in semantic parsing for open-domain question answering by generating paraphrases of input questions to improve mapping to knowledge-base queries, resulting in significant performance improvements on the WebQuestions benchmark dataset.
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 of the input question with the goal that at least one of them will be correctly mapped to a 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 the WebQuestions benchmark dataset show that the performance of the semantic parser significantly improves over strong baselines.