Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment

TL;DR

This paper introduces a method for automatically generating gap-focused questions in educational dialogues to identify and address information gaps, enhancing interactive learning experiences.

Contribution

It defines the task of gap-focused question generation, proposes a model to produce such questions, and evaluates its performance against human-generated questions.

Findings

Generated questions are competitive with human questions.

The model effectively identifies key information gaps.

Human evaluation shows promising results.

Abstract

Human communication often involves information gaps between the interlocutors. For example, in an educational dialogue, a student often provides an answer that is incomplete, and there is a gap between this answer and the perfect one expected by the teacher. Successful dialogue then hinges on the teacher asking about this gap in an effective manner, thus creating a rich and interactive educational experience. We focus on the problem of generating such gap-focused questions (GFQs) automatically. We define the task, highlight key desired aspects of a good GFQ, and propose a model that satisfies these. Finally, we provide an evaluation by human annotators of our generated questions compared against human generated ones, demonstrating competitive performance.