Genericity

Data

pred (coming soon), arg (coming soon)

About

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 annotate both predicates and their arguments for kind v. individual reference and construct models for predicting this distinction. This approach moves beyond the traditional classification of sentences into generics, habituals, and episodics by decomposing these classes into component parts based in referential phenomena.

Researchers

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