Machine Comprehension by Text-to-Text Neural Question Generation
Computation and Language
2017-05-16 v2
Abstract
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.
Cite
@article{arxiv.1705.02012,
title = {Machine Comprehension by Text-to-Text Neural Question Generation},
author = {Xingdi Yuan and Tong Wang and Caglar Gulcehre and Alessandro Sordoni and Philip Bachman and Sandeep Subramanian and Saizheng Zhang and Adam Trischler},
journal= {arXiv preprint arXiv:1705.02012},
year = {2017}
}