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.
翻译:受过培训的大型神经语言模型(LM)具有非常强大的生成文本能力,但实际上很难为创造性目的加以控制。我们描述了一个插和插控制语言生成框架(插和插),允许人类用户输入多种控制代码(专题 ) 。在自动故事生成方面,这允许人类用户对主题进行松散或细微的控制,以及它们之间的过渡,这些将出现在生成的故事中,甚至可以允许重叠和混合的主题。自动化评估展示了我们的框架,与不同的基因化的LMS合作,将生成控制到具有连续加权控制代码,同时保持生成的句子流畅,显示出强大的混合能力。 人类参与者评估显示,生成的故事在两个主题之间发生了不易的转变。