Few-shot dialogue generation without annotated data: A transfer learning approach

Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon

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

4 Citations (Scopus)

Abstract

Learning with minimal data is one of the key challenges in the development of practical, production-ready goal-oriented dialogue systems. In a real-world enterprise setting where dialogue systems are developed rapidly and are expected to work robustly for an ever-growing variety of domains, products, and scenarios, efficient learning from a limited number of examples becomes indispensable. In this paper, we introduce a technique to achieve state-of-the-art dialogue generation performance in a few-shot setup, without using any annotated data. We do this by leveraging background knowledge from a larger, more highly represented dialogue source — namely, the MetaLWOz dataset. We evaluate our model on the Stanford Multi-Domain Dialogue Dataset, consisting of human-human goal-oriented dialogues in in-car navigation, appointment scheduling, and weather information domains. We show that our few-shot approach achieves state-of-the art results on that dataset by consistently outperforming the previous best model in terms of BLEU and Entity F1 scores, while being more data-efficient by not requiring any data annotation.

Original languageEnglish
Title of host publicationProceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
PublisherAssociation for Computational Linguistics
Pages32-39
Number of pages8
ISBN (Electronic)9781950737611
DOIs
Publication statusPublished - Sep 2019
Event20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019 - Stockholm, Sweden
Duration: 11 Sep 201913 Sep 2019

Conference

Conference20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019
Abbreviated titleSIGDIAL 2019
Country/TerritorySweden
CityStockholm
Period11/09/1913/09/19

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Few-shot dialogue generation without annotated data: A transfer learning approach'. Together they form a unique fingerprint.

Cite this