Abstract

Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set. However, the lack of high-quality dialog data and the expensive data annotation process greatly limit their application in real world settings. We propose a paraphrase augmented response generation (PARG) framework that jointly trains a paraphrase model and a response generation model to improve the dialog generation performance. We also design a method to automatically construct paraphrase training data set based on dialog state and dialog act labels. PARG is applicable to various dialog generation models, such as TSCP (Lei et al., 2018) and DAMD (Zhang et al., 2019). Experimental results show that the proposed framework improves these state-of-the-art dialog models further on CamRest676 and MultiWOZ. PARG also outperforms other data augmentation methods significantly in dialog generation tasks, especially under low resource settings.

Highlights

  • Task-oriented dialog systems that are applied to restaurant reservation and ticket booking have attracted extensive attention recently (Young et al, 2013; Wen et al, 2017; Bordes et al, 2016; Eric and Manning, 2017)

  • We propose the Paraphrase Augmented Response Generation (PARG), an effective learning Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 639–649 July 5 - 10, 2020. c 2020 Association for Computational Linguistics framework that jointly optimizes dialog paraphrase and dialog response generation

  • We introduce an attention connection between the paraphrase decoder and the belief span decoder to allow the gradient in the response generation model to back-propagate to the paraphrase generation model

Read more

Summary

Introduction

Task-oriented dialog systems that are applied to restaurant reservation and ticket booking have attracted extensive attention recently (Young et al, 2013; Wen et al, 2017; Bordes et al, 2016; Eric and Manning, 2017). With the progress on sequence-to-sequence (seq2seq) learning (Sutskever et al, 2014), neural generative models have achieved promising performance on dialog response generation (Zhao et al, 2017; Lei et al, 2018; Zhang et al, 2019). Training such models requires a large amount of high-quality dialog data. We propose automated data augmentation methods to expand existing well-annotated dialog datasets, and thereby train better dialog systems

Objectives
Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.