Sogou Machine Reading Comprehension Toolkit
This toolkit addresses the problem of slow and complex development for researchers and practitioners in machine reading comprehension, but it is incremental as it builds on existing models and methods.
The authors tackled the need for efficient development of machine reading comprehension models by introducing the Sogou Machine Reading Comprehension (SMRC) toolkit, which provides dataset readers, a preprocessing pipeline, neural network components, and built-in models to streamline data preparation, model construction, and training.
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.