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

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...

Full description

Bibliographic Details
Main Authors:	Govindarajan, Venkata, Durme, Benjamin Van, White, Aaron Steven
Format:	Article
Language:	English
Published:	The MIT Press 2019-11-01
Series:	Transactions of the Association for Computational Linguistics
Online Access:	https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00285

id	doaj-2649263298ae45bf8ee1668325d15bf3
record_format	Article
spelling	doaj-2649263298ae45bf8ee1668325d15bf32020-11-25T02:00:22ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2019-11-01750151710.1162/tacl_a_00285Decomposing Generalization: Models of Generic, Habitual, and Episodic StatementsGovindarajan, VenkataDurme, Benjamin VanWhite, Aaron Steven 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. https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00285
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Govindarajan, Venkata Durme, Benjamin Van White, Aaron Steven
spellingShingle	Govindarajan, Venkata Durme, Benjamin Van White, Aaron Steven Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements Transactions of the Association for Computational Linguistics
author_facet	Govindarajan, Venkata Durme, Benjamin Van White, Aaron Steven
author_sort	Govindarajan, Venkata
title	Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
title_short	Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
title_full	Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
title_fullStr	Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
title_full_unstemmed	Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
title_sort	decomposing generalization: models of generic, habitual, and episodic statements
publisher	The MIT Press
series	Transactions of the Association for Computational Linguistics
issn	2307-387X
publishDate	2019-11-01
description	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.
url	https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00285
work_keys_str_mv	AT govindarajanvenkata decomposinggeneralizationmodelsofgenerichabitualandepisodicstatements AT durmebenjaminvan decomposinggeneralizationmodelsofgenerichabitualandepisodicstatements AT whiteaaronsteven decomposinggeneralizationmodelsofgenerichabitualandepisodicstatements
_version_	1724961025495662592

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

Similar Items