Abstract

Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be adapted to meet this requirement — therefore, reducing the amount of data and annotations necessary for training such systems is a central research problem. In this paper, we present the Dialogue Knowledge Transfer Network (DiKTNet), a state-of-the-art approach to goal-oriented dialogue generation which only uses a few example dialogues (i.e. few-shot learning), none of which has to be annotated. We achieve this by performing a 2-stage training. Firstly, we perform unsupervised dialogue representation pre-training on a large source of goal-oriented dialogues in multiple domains, the MetaLWOz corpus. Secondly, at the transfer stage, we train DiKTNet using this representation together with 2 other textual knowledge sources with different levels of generality: ELMo encoder and the main dataset’s source domains. Our main dataset is the Stanford Multi-Domain dialogue corpus. We evaluate our model on it in terms of BLEU and Entity F1 scores, and show that our approach significantly and consistently improves upon a series of baseline models as well as over the previous state-of-the-art dialogue generation model, ZSDG. The improvement upon the latter — up to 10% in Entity F1 and the average of 3% in BLEU score — is achieved using only 10% equivalent of ZSDG’s in-domain training data.

Highlights

  • Machine learning-based dialogue systems, while still being a relatively new research direction, are experiencing increasingly wide adoption in industry

  • We present the Dialogue Knowledge Transfer Network, a generative goal-oriented dialogue model designed for fewshot learning, i.e. training only using a small number of complete in-domain dialogues

  • While improvements upon Zero-Shot Dialogue Generation (ZSDG) can already be seen with simple Hierarchical Encoder-Decoder (HRED) in a fewshot setup, the use of the Latent Action EncoderDecoder (LAED) representation and domain-general ELMo encoding helps significantly reduce the amount of in-domain training data needed: at 1% of in-domain dialogues, we see that Dialogue Knowledge Transfer Network (DiKTNet) consistently and significantly improves upon ZSDG in every domain

Read more

Summary

Introduction

Machine learning-based dialogue systems, while still being a relatively new research direction, are experiencing increasingly wide adoption in industry. Products like Google Dialogflow, Wit.ai, Microsoft LUIS, and Rasa offer means for rapid development of a dialogue system’s core modules. With the recently adopted technique of training dialogue systems end-to-end data-efficiency of such systems becomes the key question in their adoption in practical applications. Ultes et al (2018); Wen et al (2017); Rojas-Barahona et al (2017)), such systems have too high data consumption — including both collection and annotation effort — in order for them to be used in rapidly paced industrial product cycles. Approaches to training such systems with extremely limited data (i.e. zero-, one- and few-shot training) are a priority research direction in the dialogue systems area

Methods
Results
Discussion
Conclusion

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.