Paraphrase Generation for Semi-Supervised Learning in

Eunah Cho, He Xie, William M. Campbell
2019 Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation   unpublished
Semi-supervised learning is an efficient way to improve performance for natural language processing systems. In this work, we propose Para-SSL, a scheme to generate candidate utterances using paraphrasing and methods from semi-supervised learning. In order to perform paraphrase generation in the context of a dialog system, we automatically extract paraphrase pairs to create a paraphrase corpus. Using this data, we build a paraphrase generation system and perform one-to-many generation, followed
more » ... by a validation step to select only the utterances with good quality. The paraphrasebased semi-supervised learning is applied to five functionalities in a natural language understanding system. Our proposed method for semi-supervised learning using paraphrase generation does not require user utterances and can be applied prior to releasing a new functionality to a system. Experiments show that we can achieve up to 19% of relative semantic error reduction without an access to user utterances, and up to 35% when leveraging live traffic utterances.
doi:10.18653/v1/w19-2306 fatcat:scrsvohq6vhwrbos6hoa7swm3u