Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
Venkata Subrahmanyan Govindarajan, Benjamin Van Durme, Aaron Steven White
January 2019
 

We present a novel semantic framework for modeling linguistic expressions of generalization - generic, habitual, and episodic statements - as combinations of simple, real-valued referential properties of predicates and their arguments. We use this framework to construct a dataset covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to probe the efficacy of type-level and token-level information - including hand-engineered features and contextual and non-contextual word embeddings - for predicting expressions of generalization. Data and code are available at decomp.io.
Format: [ pdf ]
Reference: lingbuzz/004435
(please use that when you cite this article)
Published in:
keywords: generic, habitual, episodic, kind, abstract, concreteness, reference, corpus, universal decompositional semantics, neural network, semantics
Downloaded:58 times

 

[ edit this article | back to article list ]