Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification

Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.

Guardado en:

Detalles Bibliográficos
Autores principales:	Ludovica Pannitto, Lavinia Salicchi, Alessandro Lenci
Formato:	article
Lenguaje:	EN
Publicado:	Accademia University Press 2018
Materias:	Social Sciences H Computational linguistics. Natural language processing P98-98.5
Acceso en línea:	https://doaj.org/article/da6f8ecc065a4a64bb29d283593ac08e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:da6f8ecc065a4a64bb29d283593ac08e
record_format	dspace
spelling	oai:doaj.org-article:da6f8ecc065a4a64bb29d283593ac08e2021-12-02T09:52:32ZRefining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification2499-455310.4000/ijcol.506https://doaj.org/article/da6f8ecc065a4a64bb29d283593ac08e2018-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/506https://doaj.org/toc/2499-4553Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.Ludovica PannittoLavinia SalicchiAlessandro LenciAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 4, Iss 2, Pp 45-55 (2018)
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 Ludovica Pannitto Lavinia Salicchi Alessandro Lenci Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
description	Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.
format	article
author	Ludovica Pannitto Lavinia Salicchi Alessandro Lenci
author_facet	Ludovica Pannitto Lavinia Salicchi Alessandro Lenci
author_sort	Ludovica Pannitto
title	Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
title_short	Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
title_full	Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
title_fullStr	Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
title_full_unstemmed	Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification
title_sort	refining the distributional inclusion hypothesis for unsupervised hypernym identification
publisher	Accademia University Press
publishDate	2018
url	https://doaj.org/article/da6f8ecc065a4a64bb29d283593ac08e
work_keys_str_mv	AT ludovicapannitto refiningthedistributionalinclusionhypothesisforunsupervisedhypernymidentification AT laviniasalicchi refiningthedistributionalinclusionhypothesisforunsupervisedhypernymidentification AT alessandrolenci refiningthedistributionalinclusionhypothesisforunsupervisedhypernymidentification
_version_	1718397973948268544

Refining the Distributional Inclusion Hypothesis for Unsupervised Hypernym Identification

Ejemplares similares