EQG-RACE: Examination-Type Question Generation

TL;DR

This paper introduces EQG-RACE, a novel question generation method that produces exam-like questions from RACE dataset, employing answer tagging and graph networks, achieving state-of-the-art results and establishing a new benchmark.

Contribution

The paper presents a new examination-type question generation approach using a dataset from RACE, with innovative answer tagging and graph-based reasoning techniques.

Findings

Achieves state-of-the-art performance on exam-like question generation.

Outperforms existing baselines in quality and relevance.

Provides a new benchmark dataset and method for future research.

Abstract

Question Generation (QG) is an essential component of the automatic intelligent tutoring systems, which aims to generate high-quality questions for facilitating the reading practice and assessments. However, existing QG technologies encounter several key issues concerning the biased and unnatural language sources of datasets which are mainly obtained from the Web (e.g. SQuAD). In this paper, we propose an innovative Examination-type Question Generation approach (EQG-RACE) to generate exam-like questions based on a dataset extracted from RACE. Two main strategies are employed in EQG-RACE for dealing with discrete answer information and reasoning among long contexts. A Rough Answer and Key Sentence Tagging scheme is utilized to enhance the representations of input. An Answer-guided Graph Convolutional Network (AG-GCN) is designed to capture structure information in revealing the inter-sentences and intra-sentence relations. Experimental results show a state-of-the-art performance of EQG-RACE, which is apparently superior to the baselines. In addition, our work has established a new QG prototype with a reshaped dataset and QG method, which provides an important benchmark for related research in future work. We will make our data and code publicly available for further research.