谷歌浏览器插件
订阅小程序
在清言上使用

Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes

Artificial Intelligence and Interactive Digital Entertainment Conference(2021)

引用 4|浏览19
暂无评分
摘要
Large pre-trained neural language models (LM) have very powerful text generation capabilities. However, in practice, they are hard to control for creative purposes. We describe a Plug-and-Play controllable language generation framework, Plug-and-Blend, that allows a human user to input multiple control codes (topics). In the context of automated story generation, this allows a human user loose or fine-grained control of the topics and transitions between them that will appear in the generated story, and can even allow for overlapping, blended topics. Automated evaluations show our framework, working with different generative LMs, controls the generation towards given continuous-weighted control codes while keeping the generated sentences fluent, demonstrating strong blending capability. A human participant evaluation shows that the generated stories are observably transitioning between two topics.
更多
查看译文
关键词
Topic Modeling,Language Modeling,Language Understanding
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要