Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge

TL;DR

This paper introduces a model for generating clarification questions by leveraging global knowledge to identify missing information and determine usefulness, improving over existing methods in reducing ambiguity.

Contribution

The paper proposes a novel approach that uses global and local views to generate more effective clarification questions, outperforming baselines in automatic and human evaluations.

Findings

Model outperforms baselines in automatic metrics

Model is preferred in human evaluations

Effective in reducing ambiguity in context understanding

Abstract

The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to form a global view and compare it to the given context to ascertain what is missing and what is useful in the context. Inspired by this, we propose a model for clarification question generation where we first identify what is missing by taking a difference between the global and the local view and then train a model to identify what is useful and generate a question about it. Our model outperforms several baselines as judged by both automatic metrics and humans.