MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform
This provides a tool for developers and researchers to quickly prototype text generation demos, though it is incremental as it builds on existing algorithms.
The authors tackled the problem of building demos for knowledge-grounded stylized text generation by developing MixingBoard, a platform that unifies existing text generation algorithms, adapts them for constrained generation, and implements cross-model integration strategies with external knowledge retrieval.
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.