Generating Highly Relevant Questions
This addresses the issue of low-quality question generation for educational or QA systems, but it is incremental as it builds on existing seq2seq methods.
The paper tackled the problem of neural seq2seq question generation producing generic and poorly relevant questions by proposing a partial copy mechanism and a QA-based reranker, resulting in substantial improvements in relevance.
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.