Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users
This work addresses the problem of rapid development for new tasks or languages in dialogue systems, though it appears incremental as it builds on existing on-line learning approaches.
The paper tackles the challenge of data acquisition and batch training limitations in dialogue systems by proposing on-line joint reinforcement learning for semantic parsing and dialogue management, achieving good performance with only a few hundred training dialogues and surpassing a handcrafted system.
Design of dialogue systems has witnessed many advances lately, yet acquiring huge set of data remains an hindrance to their fast development for a new task or language. Besides, training interactive systems with batch data is not satisfactory. On-line learning is pursued in this paper as a convenient way to alleviate these difficulties. After the system modules are initiated, a single process handles data collection, annotation and use in training algorithms. A new challenge is to control the cost of the on-line learning borne by the user. Our work focuses on learning the semantic parsing and dialogue management modules (speech recognition and synthesis offer ready-for-use solutions). In this context we investigate several variants of simultaneous learning which are tested in user trials. In our experiments, with varying merits, they can all achieve good performance with only a few hundreds of training dialogues and overstep a handcrafted system. The analysis of these experiments gives us some insights, discussed in the paper, into the difficulty for the system's trainers to establish a coherent and constant behavioural strategy to enable a fast and good-quality training phase.