Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Govindarajan, Venkata Subrahmanyan, Van Durme, Benjamin, White, Aaron Steven
Natura: Preprint
Pubblicazione: 2019
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911596820824064
author Govindarajan, Venkata Subrahmanyan
Van Durme, Benjamin
White, Aaron Steven
author_facet Govindarajan, Venkata Subrahmanyan
Van Durme, Benjamin
White, Aaron Steven
contents 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 static (GloVe) and contextual (ELMo) word embeddings---for predicting expressions of generalization. Data and code are available at decomp.io.
format Preprint
id arxiv_https___arxiv_org_abs_1901_11429
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
Govindarajan, Venkata Subrahmanyan
Van Durme, Benjamin
White, Aaron Steven
Computation and Language
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 static (GloVe) and contextual (ELMo) word embeddings---for predicting expressions of generalization. Data and code are available at decomp.io.
title Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
topic Computation and Language
url https://arxiv.org/abs/1901.11429