InFillmore: Frame-Guided Language Generation with Bidirectional Context

By Jiefu Ou, Nathaniel Weir, Anton Belyy, Felix X. Yu, Benjamin Van Durme. 2021

5 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Matt Gardner
2. Matthew E. Peters
3. Hao Peng
4. Tongshuang Sherry Wu
5. Alexis Ross
6. Mohit Bansal
7. Noah A. Smith
8. Luke S. Zettlemoyer

In Information Systems

1. Tongshuang Sherry Wu
2. Matt Gardner
3. Hao Peng
4. Matthew E. Peters
5. Ana Marasovic

In Natural Language Processing

1. Matt Gardner
2. Matthew E. Peters
3. Tongshuang Sherry Wu
4. Hao Peng
5. Alexis Ross
6. Mohit Bansal
7. Luke S. Zettlemoyer
8. Jonathan Berant

Citations in the corpus

• Tailor: Generating and Perturbing Text with Semantic Controls (2021, background): “While InFillmore tunes the higher-level semantics of a sentence, T ailor ’s semantic controls incorporate fine-grained information about the location and semantics of textual phrases; in addition, we demonstrate two new applications for semantically-guided generation, contrast set generation and data”