Light-weight, easy to start.
Don't bother your way to construct models.
Predefined standard datasets, in the domain of language modeling, dialog generation and more.
A dashboard to show the performance, compare your and others' models fairly.
Predefined evaluation suites, test your model with multiple metrics in several lines.
Complete and configurable framework for task-oriented dialog system.
Pre-trained models on Multiwoz, Camrest, Dealornot dataset.
Simple interfaces for adapting your models.
Rule simulators on Multiwoz and Camrest dataset for RL policy training.