We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental and semantic grammar - Dynamic Syntax (DS) - allows systems to discover, generate, and understand many new dialogue variants. The method avoids the use of expensive and time-consuming dialogue act annotations, and supports more natural (incremental) dialogues than turn-based systems. Here, language generation and dialogue management are treated as a joint decision/optimisation problem, and the MDP model for RL is constructed automatically. With an implemented system, we show that this method enables a wide range of dialogue variations to be automatically captured, even when the system is trained from only a single dialogue. The variants include question-answer pairs, over- and under-answering, self- and other-corrections, clarification interaction, split-utterances, and ellipsis. This generalisation property results from the structural knowledge and constraints present within the DS grammar, and highlights some limitations of recent systems built using machine learning techniques only.
|Publication status||Published - 2016|
|Event||30th Conference on Neural Information Processing Systems 2016 - Barcelona, Spain|
Duration: 5 Dec 2016 → 10 Dec 2016
|Conference||30th Conference on Neural Information Processing Systems 2016|
|Abbreviated title||NIPS 2016|
|Period||5/12/16 → 10/12/16|