Towards Enriched Controllability for Educational Question Generation

TL;DR

This paper introduces a new controllability attribute called question explicitness for educational question generation, enabling more nuanced control over generated questions from children stories, with preliminary evidence supporting its effectiveness.

Contribution

It proposes a novel guidance attribute, question explicitness, to enhance controllability in educational question generation models, allowing explicit and implicit question generation control.

Findings

Preliminary evidence shows controllability via question explicitness.

Ability to generate both explicit and implicit questions.

Code implementation is publicly available.

Abstract

Question Generation (QG) is a task within Natural Language Processing (NLP) that involves automatically generating questions given an input, typically composed of a text and a target answer. Recent work on QG aims to control the type of generated questions so that they meet educational needs. A remarkable example of controllability in educational QG is the generation of questions underlying certain narrative elements, e.g., causal relationship, outcome resolution, or prediction. This study aims to enrich controllability in QG by introducing a new guidance attribute: question explicitness. We propose to control the generation of explicit and implicit wh-questions from children-friendly stories. We show preliminary evidence of controlling QG via question explicitness alone and simultaneously with another target attribute: the question's narrative element. The code is publicly available at github.com/bernardoleite/question-generation-control.