Interactive Question Clarification in Dialogue via Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning approach to improve dialogue systems by asking clarifying questions to resolve ambiguous user queries, leading to more accurate responses.

Contribution

It proposes a novel reinforcement learning model that refines ambiguous questions through intent label suggestions, enhancing dialogue system clarity and response accuracy.

Findings

Significant improvement in user click metrics

Effective query clarification through intent label selection

Robust performance across multiple experiments

Abstract

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.