InFillmore: Frame-Guided Language Generation with Bidirectional Context

Abstract

We propose a structured extension to bidirectional-context conditional language generation, or "infilling," inspired by Frame Semantic theory (Fillmore, 1976). Guidance is provided through two approaches: (1) model fine-tuning, conditioning directly on observed symbolic frames, and (2) a novel extension to disjunctive lexically constrained decoding that leverages frame semantic lexical units. Automatic and human evaluations confirm that frame-guided generation allows for explicit manipulation of intended infill semantics, with minimal loss in distinguishability from human-generated text. Our methods flexibly apply to a variety of use scenarios, and we provide a codebase and interactive demo available from https://nlp.jhu.edu/demos/infillmore.

Appearing in *SEM 2021

References in corpus (6)

• Story Generation from Sequence of Independent Short Descriptions
• PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
• Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
• NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
• Learning to Predict Explainable Plots for Neural Story Generation
• Learning Efficient Lexically-Constrained Neural Machine Translation with External Memory