# Machine Comprehension by Text-to-Text Neural Question Generation

## TL;DR

This paper introduces a neural question generation model that creates natural questions from documents, trained with supervised and reinforcement learning, aiming to enhance question-answering system performance.

## Contribution

The paper presents a novel recurrent neural model for question generation conditioned on answers, combining supervised training with reinforcement learning to optimize question quality.

## Key findings

- Model improves question quality metrics
- Question generation enhances QA system performance
- Reinforcement learning fine-tuning yields better questions

## 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.