Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding

TL;DR

This paper presents a neural self-attentive model that intelligently decides when a conversational agent should ask clarifying questions, improving user experience by reducing unnecessary queries in large-scale spoken language understanding.

Contribution

It introduces a novel neural model that leverages ambiguity hypotheses and context to determine the necessity of clarifying questions, enhancing dialogue efficiency.

Findings

Significant improvement over baseline methods in ambiguity resolution.

Effective handling of five common ambiguity types.

Validated on real data from a commercial conversational agent.

Abstract

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.