论文标题
搅拌板：知识渊博的风格化集成文本生成平台
MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform
论文作者
论文摘要
我们提出搅拌板，这是一个快速构建演示的平台，重点是知识接地的风格化文本生成。我们在共享代码库中统一了现有的文本生成算法，并进一步适应了早期的算法以生成约束。要从不同模型中借用优势，我们实施了跨模型集成的策略，从令牌概率级别到潜在的空间级别。通过一个模块提供了外部知识的接口，该模块可以从网络或任何文档集合中检索即时相关的知识。提供了用于本地开发的用户界面，远程网页访问和RESTFUL API，以使用户可以简单地构建自己的演示。
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.
