Machine reading comprehension have been intensively studied in recent years, and neural network-based models have shown dominant performances. In this paper, we present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes. To achieve this goal, the toolkit provides dataset readers, a flexible preprocessing pipeline, necessary neural network components, and built-in models, which make the whole process of data preparation, model construction, and training easier.
@article{arxiv.1903.11848,
title = {Sogou Machine Reading Comprehension Toolkit},
author = {Jindou Wu and Yunlun Yang and Chao Deng and Hongyi Tang and Bingning Wang and Haoze Sun and Ting Yao and Qi Zhang},
journal= {arXiv preprint arXiv:1903.11848},
year = {2019}
}