An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework

Thematic fit is the extent to which an entity fits a thematic role in the semantic frame of an event, e.g., how well humans would rate “knife” as an instrument of an event of cutting. We explore the use of the SENNA semantic role-labeller in defining a distributional space in order to build an unsup...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Asad Sayeed, Pavel Shkadzko, Vera Demberg
Formato:	article
Lenguaje:	EN
Publicado:	Accademia University Press 2015
Materias:	Social Sciences H Computational linguistics. Natural language processing P98-98.5
Acceso en línea:	https://doaj.org/article/e4eff677d29d4642908edcf2654f66b7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e4eff677d29d4642908edcf2654f66b7
record_format	dspace
spelling	oai:doaj.org-article:e4eff677d29d4642908edcf2654f66b72021-12-02T09:52:19ZAn Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework2499-455310.4000/ijcol.298https://doaj.org/article/e4eff677d29d4642908edcf2654f66b72015-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/298https://doaj.org/toc/2499-4553Thematic fit is the extent to which an entity fits a thematic role in the semantic frame of an event, e.g., how well humans would rate “knife” as an instrument of an event of cutting. We explore the use of the SENNA semantic role-labeller in defining a distributional space in order to build an unsupervised model of event-entity thematic fit judgements. We test a number of ways of extracting features from SENNA-labelled versions of the ukWaC and BNC corpora and identify tradeoffs. Some of our Distributional Memory models outperform an existing syntax-based model (TypeDM) that uses hand-crafted rules for role inference on a previously tested data set. We combine the results of a selected SENNA-based model with TypeDM’s results and find that there is some amount of complementarity in what a syntactic and a semantic model will cover. In the process, we create a broad-coverage semantically-labelled corpus.Asad SayeedPavel ShkadzkoVera DembergAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 1, Iss 1, Pp 31-46 (2015)
institution	DOAJ
collection	DOAJ
language	EN
topic	Social Sciences H Computational linguistics. Natural language processing P98-98.5
spellingShingle	Social Sciences H Computational linguistics. Natural language processing P98-98.5 Asad Sayeed Pavel Shkadzko Vera Demberg An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework
description	Thematic fit is the extent to which an entity fits a thematic role in the semantic frame of an event, e.g., how well humans would rate “knife” as an instrument of an event of cutting. We explore the use of the SENNA semantic role-labeller in defining a distributional space in order to build an unsupervised model of event-entity thematic fit judgements. We test a number of ways of extracting features from SENNA-labelled versions of the ukWaC and BNC corpora and identify tradeoffs. Some of our Distributional Memory models outperform an existing syntax-based model (TypeDM) that uses hand-crafted rules for role inference on a previously tested data set. We combine the results of a selected SENNA-based model with TypeDM’s results and find that there is some amount of complementarity in what a syntactic and a semantic model will cover. In the process, we create a broad-coverage semantically-labelled corpus.
format	article
author	Asad Sayeed Pavel Shkadzko Vera Demberg
author_facet	Asad Sayeed Pavel Shkadzko Vera Demberg
author_sort	Asad Sayeed
title	An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework
title_short	An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework
title_full	An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework
title_fullStr	An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework
title_full_unstemmed	An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework
title_sort	exploration of semantic features in an unsupervised thematic fit evaluation framework
publisher	Accademia University Press
publishDate	2015
url	https://doaj.org/article/e4eff677d29d4642908edcf2654f66b7
work_keys_str_mv	AT asadsayeed anexplorationofsemanticfeaturesinanunsupervisedthematicfitevaluationframework AT pavelshkadzko anexplorationofsemanticfeaturesinanunsupervisedthematicfitevaluationframework AT verademberg anexplorationofsemanticfeaturesinanunsupervisedthematicfitevaluationframework AT asadsayeed explorationofsemanticfeaturesinanunsupervisedthematicfitevaluationframework AT pavelshkadzko explorationofsemanticfeaturesinanunsupervisedthematicfitevaluationframework AT verademberg explorationofsemanticfeaturesinanunsupervisedthematicfitevaluationframework
_version_	1718397977419055104

An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework

Ejemplares similares