MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform

Xiang Gao, Michel Galley, Bill Dolan


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 a 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.
Anthology ID:
2020.acl-demos.26
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Month:
July
Year:
2020
Address:
Online
Editors:
Asli Celikyilmaz, Tsung-Hsien Wen
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
224–231
Language:
URL:
https://aclanthology.org/2020.acl-demos.26
DOI:
10.18653/v1/2020.acl-demos.26
Bibkey:
Cite (ACL):
Xiang Gao, Michel Galley, and Bill Dolan. 2020. MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 224–231, Online. Association for Computational Linguistics.
Cite (Informal):
MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform (Gao et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.acl-demos.26.pdf
Video:
 http://slideslive.com/38928584
Code
 microsoft/MixingBoard