Interactive Question Clarification in Dialogue via Reinforcement Learning
This work provides an incremental improvement for dialogue systems struggling with ambiguous user queries, benefiting users by enabling more precise intent identification.
This paper addresses the problem of ambiguous questions in dialogue systems by proposing a reinforcement learning model that clarifies user queries. The model suggests refinements of the original query by presenting a set of intent phrases to the user, leading to significant improvements in real-world user click metrics.
Coping with ambiguous questions has been a perennial problem in real-world dialogue systems. Although clarification by asking questions is a common form of human interaction, it is hard to define appropriate questions to elicit more specific intents from a user. In this work, we propose a reinforcement model to clarify ambiguous questions by suggesting refinements of the original query. We first formulate a collection partitioning problem to select a set of labels enabling us to distinguish potential unambiguous intents. We list the chosen labels as intent phrases to the user for further confirmation. The selected label along with the original user query then serves as a refined query, for which a suitable response can more easily be identified. The model is trained using reinforcement learning with a deep policy network. We evaluate our model based on real-world user clicks and demonstrate significant improvements across several different experiments.