Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge
This work addresses ambiguity reduction in dialogue systems, but it is incremental as it builds on existing methods for question generation.
The paper tackled the problem of generating clarification questions to reduce ambiguity by identifying missing and useful information in a given context, and the result was a model that outperformed baselines in both automatic metrics and human evaluations.
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.