Zero-Shot Dialog Generation with Cross-Domain Latent Actions

Abstract

This paper introduces zero-shot dialog generation (ZSDG), as a step towards neural dialog systems that can instantly generalize to new situations with minimal data. ZSDG enables an end-to-end generative dialog system to generalize to a new domain for which only a domain description is provided and no training dialogs are available. Then a novel learning framework, Action Matching, is proposed. This algorithm can learn a cross-domain embedding space that models the semantics of dialog responses which, in turn, lets a neural dialog generation model generalize to new domains. We evaluate our methods on a new synthetic dialog dataset, and an existing human-human dialog dataset. Results show that our method has superior performance in learning dialog models that rapidly adapt their behavior to new domains and suggests promising future research.

Accepted as a long paper in SIGDIAL 2018

References in corpus (6)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Recurrent Neural Network Regularization
• Pointer Sentinel Mixture Models
• One-Shot Imitation Learning
• A Hierarchical Neural Autoencoder for Paragraphs and Documents
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability

Cited by in corpus (11)

• Neural Language Generation: Formulation, Methods, and Evaluation
• MALA: Cross-Domain Dialogue Generation with Action Learning
• Unsupervised Dialog Structure Learning
• Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges
• Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation
• Elastic CRFs for Open-ontology Slot Filling
• Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming
• Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play
• DSBERT:Unsupervised Dialogue Structure learning with BERT
• When is it permissible for artificial intelligence to lie? A trust-based approach
• A Corpus-free State2Seq User Simulator for Task-oriented Dialogue