Generating Highly Relevant Questions

TL;DR

This paper introduces two methods to improve neural question generation by enhancing relevance and diversity, using a partial copy mechanism and a QA-based reranker, leading to more pertinent questions.

Contribution

It presents novel techniques combining copy mechanisms and reranking to significantly enhance question relevance in neural question generation models.

Findings

Improved relevance of generated questions to passages and answers.

Enhanced diversity in question generation.

Significant performance gains demonstrated through experiments.

Abstract

The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer. In this paper, we propose two methods to address the issue. (1) By a partial copy mechanism, we prioritize words that are morphologically close to words in the input passage when generating questions; (2) By a QA-based reranker, from the n-best list of question candidates, we select questions that are preferred by both the QA and QG model. Experiments and analyses demonstrate that the proposed two methods substantially improve the relevance of generated questions to passages and answers.