An important line of study in formal semantics, philosophy, and AI investigates how language is used to represent knowledge of kinds, regularities and patterns. For instance, how do we know that lions roar describes a generalization about a kind of thing (lions), while those lions roared describes a specific event in which particular lions participated?

In this line of work, we propose a novel framework for capturing linguistic expressions of generalization. We suggest that linguistic expressions of generalization should be captured in a continuous multi-label system, rather than a multi-class system. We do this by decomposing categories such as EPISODIC, HABITUAL, and GENERIC into simple referential properties of predicates and their arguments.

Data

Train Dev Test Download Citation
26721 3274 3119 pred (zip) Govindarajan et al. 2019
30035 3611 3500 arg (zip) Govindarajan et al. 2019

References

Govindarajan, Venkata, Benjamin Van Durme, and Aaron Steven White. 2019. Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements. Transactions of the Association for Computational Linguistics 7: 501–517. [pdf, doi, bib]

Researchers

Venkata Subrahmanyan G bio photo
Venkata Subrahmanyan G
Aaron Steven White bio photo
Aaron Steven White
Benjamin Van Durme bio photo
Benjamin Van Durme