We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet). Given a high-performing MC model in one domain, our technique aims to answer questions about documents in another domain, where we use no labeled data of question-answer pairs. Using the proposed SynNet with a pretrained model from the SQuAD dataset on the challenging NewsQA dataset, we achieve an F1 measure of 44.3% with a single model and 46.6% with an ensemble, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-of-domain baseline of 7.6%, without use of provided annotations.
@article{arxiv.1706.09789,
title = {Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension},
author = {David Golub and Po-Sen Huang and Xiaodong He and Li Deng},
journal= {arXiv preprint arXiv:1706.09789},
year = {2017}
}