English

MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform

Computation and Language 2020-07-06 v2

Abstract

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.

Keywords

Cite

@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}
}

Comments

accepted at ACL 2020

R2 v1 2026-06-23T15:36:36.760Z