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.
@article{arxiv.2103.04941,
title = {InFillmore: Frame-Guided Language Generation with Bidirectional Context},
author = {Jiefu Ou and Nathaniel Weir and Anton Belyy and Felix Yu and Benjamin Van Durme},
journal= {arXiv preprint arXiv:2103.04941},
year = {2022}
}