Data-efficient goal-oriented conversation with dialogue knowledge transfer networks

Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon

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

1 Downloads (Pure)

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.

Original languageEnglish
Title of host publicationProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing
PublisherAssociation for Computational Linguistics
Pages1741-1751
Number of pages11
ISBN (Electronic)9781950737901
DOIs
Publication statusPublished - 2019
Event9th International Joint Conference on Natural Language Processing 2019 - Hong Kong, China
Duration: 3 Nov 20197 Nov 2019

Conference

Conference9th International Joint Conference on Natural Language Processing 2019
Abbreviated titleEMNLP-IJCNLP 2019
CountryChina
CityHong Kong
Period3/11/197/11/19

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Data-efficient goal-oriented conversation with dialogue knowledge transfer networks'. Together they form a unique fingerprint.

  • Cite this

    Shalyminov, I., Lee, S., Eshghi, A., & Lemon, O. (2019). Data-efficient goal-oriented conversation with dialogue knowledge transfer networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (pp. 1741-1751). Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1183