DeepAI AI Chat
Log In Sign Up

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

by   Yi Cheng, et al.

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on which extensive experiments are conducted to test the performance of our method.


page 1

page 2

page 3

page 4


Difficulty Controllable Question Generation for Reading Comprehension

Question generation aims to generate natural language questions from a r...

MQA: Answering the Question via Robotic Manipulation

In this paper,we propose a novel task of Manipulation Question Answering...

Opacity, Obscurity, and the Geometry of Question-Asking

Asking questions is a pervasive human activity, but little is understood...

Stacked Attention Networks for Image Question Answering

This paper presents stacked attention networks (SANs) that learn to answ...

ClarQ: A large-scale and diverse dataset for Clarification Question Generation

Question answering and conversational systems are often baffled and need...

Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model

The ability to generate natural-language questions with controlled compl...

Simulating Problem Difficulty in Arithmetic Cognition Through Dynamic Connectionist Models

The present study aims to investigate similarities between how humans an...