Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors

The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in comparison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuri Bizzoni, Marco S. G. Senaldi, 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/1dc2e698dc53438c84328acba984c9f4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1dc2e698dc53438c84328acba984c9f4
record_format	dspace
spelling	oai:doaj.org-article:1dc2e698dc53438c84328acba984c9f42021-12-02T09:52:21ZFinding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors2499-455310.4000/ijcol.535https://doaj.org/article/1dc2e698dc53438c84328acba984c9f42018-06-01T00:00:00Zhttp://journals.openedition.org/ijcol/535https://doaj.org/toc/2499-4553The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in comparison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier previously trained to detect metaphorical bigrams. The experiments suggest that the distributional context of a given phrase is sufficient to carry out idiom type identification to a satisfactory degree, with an increase in performance when input phrases are filtered according to human-elicited idiomaticity ratings collected for the same expressions. Crucially, employing concatenations of single word vectors rather than whole-phrase vectors as training input results in the worst performance for our models, differently from what was previously registered in metaphor detection tasks.Yuri BizzoniMarco S. G. SenaldiAlessandro LenciAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 4, Iss 1, Pp 28-41 (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 Yuri Bizzoni Marco S. G. Senaldi Alessandro Lenci Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
description	The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in comparison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier previously trained to detect metaphorical bigrams. The experiments suggest that the distributional context of a given phrase is sufficient to carry out idiom type identification to a satisfactory degree, with an increase in performance when input phrases are filtered according to human-elicited idiomaticity ratings collected for the same expressions. Crucially, employing concatenations of single word vectors rather than whole-phrase vectors as training input results in the worst performance for our models, differently from what was previously registered in metaphor detection tasks.
format	article
author	Yuri Bizzoni Marco S. G. Senaldi Alessandro Lenci
author_facet	Yuri Bizzoni Marco S. G. Senaldi Alessandro Lenci
author_sort	Yuri Bizzoni
title	Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
title_short	Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
title_full	Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
title_fullStr	Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
title_full_unstemmed	Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
title_sort	finding the neural net: deep-learning idiom type identification from distributional vectors
publisher	Accademia University Press
publishDate	2018
url	https://doaj.org/article/1dc2e698dc53438c84328acba984c9f4
work_keys_str_mv	AT yuribizzoni findingtheneuralnetdeeplearningidiomtypeidentificationfromdistributionalvectors AT marcosgsenaldi findingtheneuralnetdeeplearningidiomtypeidentificationfromdistributionalvectors AT alessandrolenci findingtheneuralnetdeeplearningidiomtypeidentificationfromdistributionalvectors
_version_	1718397931947556864

Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors

Ejemplares similares