We present MixingBoard, a platform for quickly building demos with a focus on knowledge grounded stylized text generation. We unify existing text generation algorithms in a shared codebase and further adapt earlier algorithms for constrained generation. To borrow advantages from different models, we implement strategies for cross-model integration, from the token probability level to the latent space level. An interface to external knowledge is provided via a module that retrieves on-the-fly relevant knowledge from passages on the web or any document collection. A user interface for local development, remote webpage access, and a RESTful API are provided to make it simple for users to build their own demos.
@article{arxiv.2005.08365,
title = {MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform},
author = {Xiang Gao and Michel Galley and Bill Dolan},
journal= {arXiv preprint arXiv:2005.08365},
year = {2020}
}