Summary-Oriented Question Generation for Informational Queries
arXiv:2010.09692 · doi:10.18653/v1/2021.dialdoc-1.11
Abstract
Users frequently ask simple factoid questions for question answering (QA) systems, attenuating the impact of myriad recent works that support more complex questions. Prompting users with automatically generated suggested questions (SQs) can improve user understanding of QA system capabilities and thus facilitate more effective use. We aim to produce self-explanatory questions that focus on main document topics and are answerable with variable length passages as appropriate. We satisfy these requirements by using a BERT-based Pointer-Generator Network trained on the Natural Questions (NQ) dataset. Our model shows SOTA performance of SQ generation on the NQ dataset (20.1 BLEU-4). We further apply our model on out-of-domain news articles, evaluating with a QA system due to the lack of gold questions and demonstrate that our model produces better SQs for news articles -- with further confirmation via a human evaluation.
arXiv comment17 pages
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Teaching Machines to Read and Comprehend
- The Curious Case of Neural Text Degeneration
- Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
- Unsupervised Question Answering by Cloze Translation
- Learning to Generate Questions by Learning What not to Generate
- A BERT Baseline for the Natural Questions
- Recent Advances in Neural Question Generation
- What's The Latest? A Question-driven News Chatbot
- Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary
- Towards Automatic Generation of Questions from Long Answers
- Generating Followup Questions for Interpretable Multi-hop Question Answering