Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics

In this work we tested whether a series of compositionality indices that compute the distributional similarity between the vector of a given expression and the vectors of its lexical variants can effectively tell apart idiomatic and more compositional expressions in a set of 13 idiomatic and 13 non-...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marco S. G. Senaldi, Alessandro Lenci, Gianluca E. Lebani
Formato:	article
Lenguaje:	EN
Publicado:	Accademia University Press 2017
Materias:	Social Sciences H Computational linguistics. Natural language processing P98-98.5
Acceso en línea:	https://doaj.org/article/0cc7e8ae3a0f40ea80185890ef2826a1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0cc7e8ae3a0f40ea80185890ef2826a1
record_format	dspace
spelling	oai:doaj.org-article:0cc7e8ae3a0f40ea80185890ef2826a12021-12-02T09:52:34ZDetermining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics2499-455310.4000/ijcol.429https://doaj.org/article/0cc7e8ae3a0f40ea80185890ef2826a12017-06-01T00:00:00Zhttp://journals.openedition.org/ijcol/429https://doaj.org/toc/2499-4553In this work we tested whether a series of compositionality indices that compute the distributional similarity between the vector of a given expression and the vectors of its lexical variants can effectively tell apart idiomatic and more compositional expressions in a set of 13 idiomatic and 13 non-idiomatic Italian target noun-adjective constructions. The lexical variants were obtained by replacing the components of the original expressions with semantically related words automatically extracted from Distributional Semantic Models or manually derived from Italian MultiWordnet. Indices based on the Mean or the Centroid cosine similarity between the target and the variant vectors performed comparably or better than the addition-based measure traditionally reported in the distributional literature on compositionality.Marco S. G. SenaldiAlessandro LenciGianluca E. LebaniAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 3, Iss 1, Pp 43-58 (2017)
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 Marco S. G. Senaldi Alessandro Lenci Gianluca E. Lebani Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
description	In this work we tested whether a series of compositionality indices that compute the distributional similarity between the vector of a given expression and the vectors of its lexical variants can effectively tell apart idiomatic and more compositional expressions in a set of 13 idiomatic and 13 non-idiomatic Italian target noun-adjective constructions. The lexical variants were obtained by replacing the components of the original expressions with semantically related words automatically extracted from Distributional Semantic Models or manually derived from Italian MultiWordnet. Indices based on the Mean or the Centroid cosine similarity between the target and the variant vectors performed comparably or better than the addition-based measure traditionally reported in the distributional literature on compositionality.
format	article
author	Marco S. G. Senaldi Alessandro Lenci Gianluca E. Lebani
author_facet	Marco S. G. Senaldi Alessandro Lenci Gianluca E. Lebani
author_sort	Marco S. G. Senaldi
title	Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
title_short	Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
title_full	Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
title_fullStr	Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
title_full_unstemmed	Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics
title_sort	determining the compositionality of noun-adjective pairs with lexical variants and distributional semantics
publisher	Accademia University Press
publishDate	2017
url	https://doaj.org/article/0cc7e8ae3a0f40ea80185890ef2826a1
work_keys_str_mv	AT marcosgsenaldi determiningthecompositionalityofnounadjectivepairswithlexicalvariantsanddistributionalsemantics AT alessandrolenci determiningthecompositionalityofnounadjectivepairswithlexicalvariantsanddistributionalsemantics AT gianlucaelebani determiningthecompositionalityofnounadjectivepairswithlexicalvariantsanddistributionalsemantics
_version_	1718397927857061888

Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics

Ejemplares similares