Advancing Question Generation with Joint Narrative and Difficulty Control

TL;DR

This paper introduces a novel joint control strategy for generating reading comprehension questions that simultaneously manages narrative aspects and difficulty levels, aiming to enhance educational question generation.

Contribution

It proposes a new method for joint narrative and difficulty control in question generation, addressing a gap in existing research.

Findings

Preliminary evidence supports the feasibility of the joint control approach.

The strategy performs well under specific conditions.

Trade-offs in effectiveness are discussed.

Abstract

Question Generation (QG), the task of automatically generating questions from a source input, has seen significant progress in recent years. Difficulty-controllable QG (DCQG) enables control over the difficulty level of generated questions while considering the learner's ability. Additionally, narrative-controllable QG (NCQG) allows control over the narrative aspects embedded in the questions. However, research in QG lacks a focus on combining these two types of control, which is important for generating questions tailored to educational purposes. To address this gap, we propose a strategy for Joint Narrative and Difficulty Control, enabling simultaneous control over these two attributes in the generation of reading comprehension questions. Our evaluation provides preliminary evidence that this approach is feasible, though it is not effective across all instances. Our findings highlight the conditions under which the strategy performs well and discuss the trade-offs associated with its application.