2017/05/04 by Yuan, Xingdi, Wang, Tong, Gulcehre, Caglar +5 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.1705.02012
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.