Abstract Arash Eshghi 14 November 2016
BABBLE: Automatically inducing incremental dialogue systems from minimal data
Dr Arash Eshghi, Heriot Watt University
We present a method for inducing incremental dialogue systems from very small amounts of dialogue data, avoiding the use of dialogue acts. This is achieved by combining an incremental, semantic grammar formalism - Dynamic Syntax and Type Theory with Records (DS-TTR) - with Reinforcement Learning for word (action) selection, where language generation and dialogue management are treated as a joint decision/optimisation problem, and where the MDP model is constructed automatically. We show, using an implemented system, 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. For example, we show that a single training dialogue supports over 8000 new dialogues in the same domain. This generalisation property results from the structural knowledge and constraints present within the grammar, and highlights in-principle limitations of recent state-of-the-art systems that are built using machine learning techniques only.
Back to Cognitive Science Seminar Series