Machine Comprehension by Text-to-Text Neural Question Generation
TL
TL;DR
A recurrent neural model is proposed that generates natural-language questions from documents, conditioned on answers, and fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality.
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.
References52 items
1
Sentence Simplification with Deep Reinforcement Learning
2
Semi-Supervised QA with Generative Domain-Adaptive Nets
3
Batch Policy Gradient Methods for Improving Neural Conversation Models
4
Multi-Perspective Context Matching for Machine Comprehension
5