InFillmore: Frame-Guided Language Generation with Bidirectional Context
Jiefu Ou, Nathaniel Weir, Anton Belyy, Felix Yu, Benjamin Van Durme
Abstract
We propose a structured extension to bidirectional-context conditional language generation, or “infilling,” inspired by Frame Semantic theory. Guidance is provided through one of 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 an interactive web demo.- Anthology ID:
- 2021.starsem-1.12
- Volume:
- Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Lun-Wei Ku, Vivi Nastase, Ivan Vulić
- Venue:
- *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 129–142
- Language:
- URL:
- https://aclanthology.org/2021.starsem-1.12
- DOI:
- 10.18653/v1/2021.starsem-1.12
- Cite (ACL):
- Jiefu Ou, Nathaniel Weir, Anton Belyy, Felix Yu, and Benjamin Van Durme. 2021. InFillmore: Frame-Guided Language Generation with Bidirectional Context. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 129–142, Online. Association for Computational Linguistics.
- Cite (Informal):
- InFillmore: Frame-Guided Language Generation with Bidirectional Context (Ou et al., *SEM 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.starsem-1.12.pdf
- Data
- FrameNet