Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding
This addresses user experience issues in commercial conversational agents by reducing unnecessary clarifying questions, though it is incremental as it builds on existing ambiguity detection methods.
The paper tackles the problem of when to ask clarifying questions in large-scale spoken language understanding to avoid excessive questioning that harms user experience, proposing a neural self-attentive model that shows significant improvement over baselines in experiments on real data.
A large-scale conversational agent can suffer from understanding user utterances with various ambiguities such as ASR ambiguity, intent ambiguity, and hypothesis ambiguity. When ambiguities are detected, the agent should engage in a clarifying dialog to resolve the ambiguities before committing to actions. However, asking clarifying questions for all the ambiguity occurrences could lead to asking too many questions, essentially hampering the user experience. To trigger clarifying questions only when necessary for the user satisfaction, we propose a neural self-attentive model that leverages the hypotheses with ambiguities and contextual signals. We conduct extensive experiments on five common ambiguity types using real data from a large-scale commercial conversational agent and demonstrate significant improvement over a set of baseline approaches.