DeepAI AI Chat
Log In Sign Up

Zero-Shot Dialog Generation with Cross-Domain Latent Actions

by   Tiancheng Zhao, et al.
Carnegie Mellon University

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.


page 1

page 2

page 3

page 4


Schema-Guided Paradigm for Zero-Shot Dialog

Developing mechanisms that flexibly adapt dialog systems to unseen tasks...

Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema

Task-oriented dialog systems empower users to accomplish their goals by ...

Domain Adaptive Dialog Generation via Meta Learning

Domain adaptation is an essential task in dialog system building because...

Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming

Motivated by the needs of resource constrained dialog policy learning, w...

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

We propose a novel problem within end-to-end learning of task-oriented d...

Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules

In this work, we present a framework for incorporating descriptive logic...

SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting

Building end-to-end task bots and maintaining their integration with new...

Code Repositories


PyTorch codebase for zero-shot dialog generation, It is released by Tiancheng Zhao (Tony) from Dialog Research Center, LTI, CMU

view repo