Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes
Zhiyu Lin, Mark Riedl
Abstract
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 that will appear in the generated story, and can even allow for overlapping, blended topics. We show that our framework, working with different generation models, controls the generation towards given continuous-weighted control codes while keeping the generated sentences fluent, demonstrating strong blending capability.
Topics & Concepts
Computer scienceContext (archaeology)Control (management)Scheme (mathematics)Text generationPlug-inArtificial intelligenceProgramming languageMathematicsPaleontologyMathematical analysisBiologyTopic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications