Zero-Shot Dialog Generation with Cross-Domain Latent Actions
This addresses the challenge of rapid domain adaptation for dialog systems, which is incremental as it builds on existing neural methods but introduces a new zero-shot capability.
The paper tackles the problem of enabling neural dialog systems to generalize to new domains without training data by introducing zero-shot dialog generation (ZSDG) and a novel Action Matching framework, achieving superior performance in adapting to new domains on synthetic and human-human dialog datasets.
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.