We study the problem of semi-supervised question answering----utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework, the Generative Domain-Adaptive Nets. In this framework, we train a generative model to generate questions based on the unlabeled text, and combine model-generated questions with human-generated questions for training question answering models. We develop novel domain adaptation algorithms, based on reinforcement learning, to alleviate the discrepancy between the model-generated data distribution and the human-generated data distribution. Experiments show that our proposed framework obtains substantial improvement from unlabeled text.
@article{arxiv.1702.02206,
title = {Semi-Supervised QA with Generative Domain-Adaptive Nets},
author = {Zhilin Yang and Junjie Hu and Ruslan Salakhutdinov and William W. Cohen},
journal= {arXiv preprint arXiv:1702.02206},
year = {2017}
}