Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks

by   Igor Shalyminov, et al.

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 average of 3 ZSDG's in-domain training data.


page 1

page 2

page 3

page 4


Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach

Learning with minimal data is one of the key challenges in the developme...

A Simple Language Model for Task-Oriented Dialogue

Task-oriented dialogue is often decomposed into three tasks: understandi...

Data-Efficient Methods for Dialogue Systems

Conversational User Interface (CUI) has become ubiquitous in everyday li...

State-Machine-Based Dialogue Agents with Few-Shot Contextual Semantic Parsers

This paper presents a methodology and toolkit for creating a rule-based ...

Building Advanced Dialogue Managers for Goal-Oriented Dialogue Systems

Goal-Oriented (GO) Dialogue Systems, colloquially known as goal oriented...

A Corpus of Controlled Opinionated and Knowledgeable Movie Discussions for Training Neural Conversation Models

Fully data driven Chatbots for non-goal oriented dialogues are known to ...

Submodularity-inspired Data Selection for Goal-oriented Chatbot Training based on Sentence Embeddings

Goal-oriented (GO) dialogue systems rely on an initial natural language ...