Deep Learning of Inflection and the Cell-Filling Problem

Machine learning offers two basic strategies for morphology induction: lexical segmentation and surface word relation. The first approach assumes that words can be segmented into morphemes. Inferring a novel inflected form requires identification of morphemic constituents and a strategy for their re...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Franco Alberto Cardillo, Marcello Ferro, Claudia Marzi, Vito Pirrelli
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/ea47fdee18ca49449c2938cac6bdd45f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ea47fdee18ca49449c2938cac6bdd45f
record_format	dspace
spelling	oai:doaj.org-article:ea47fdee18ca49449c2938cac6bdd45f2021-12-02T09:52:21ZDeep Learning of Inflection and the Cell-Filling Problem2499-455310.4000/ijcol.540https://doaj.org/article/ea47fdee18ca49449c2938cac6bdd45f2018-06-01T00:00:00Zhttp://journals.openedition.org/ijcol/540https://doaj.org/toc/2499-4553Machine learning offers two basic strategies for morphology induction: lexical segmentation and surface word relation. The first approach assumes that words can be segmented into morphemes. Inferring a novel inflected form requires identification of morphemic constituents and a strategy for their recombination. The second approach dispenses with segmentation: lexical representations form part of a network of associatively related inflected forms. Production of a novel form consists in filling in one empty node in the network. Here, we present the results of a task of word inflection by a recurrent LSTM network that learns to fill in paradigm cells of incomplete verb paradigms. Although the task does not require morpheme segmentation, we show that accuracy in carrying out the inflection task is a function of the model’s sensitivity to paradigm distribution and morphological structure.Franco Alberto CardilloMarcello FerroClaudia MarziVito PirrelliAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 4, Iss 1, Pp 57-75 (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 Franco Alberto Cardillo Marcello Ferro Claudia Marzi Vito Pirrelli Deep Learning of Inflection and the Cell-Filling Problem
description	Machine learning offers two basic strategies for morphology induction: lexical segmentation and surface word relation. The first approach assumes that words can be segmented into morphemes. Inferring a novel inflected form requires identification of morphemic constituents and a strategy for their recombination. The second approach dispenses with segmentation: lexical representations form part of a network of associatively related inflected forms. Production of a novel form consists in filling in one empty node in the network. Here, we present the results of a task of word inflection by a recurrent LSTM network that learns to fill in paradigm cells of incomplete verb paradigms. Although the task does not require morpheme segmentation, we show that accuracy in carrying out the inflection task is a function of the model’s sensitivity to paradigm distribution and morphological structure.
format	article
author	Franco Alberto Cardillo Marcello Ferro Claudia Marzi Vito Pirrelli
author_facet	Franco Alberto Cardillo Marcello Ferro Claudia Marzi Vito Pirrelli
author_sort	Franco Alberto Cardillo
title	Deep Learning of Inflection and the Cell-Filling Problem
title_short	Deep Learning of Inflection and the Cell-Filling Problem
title_full	Deep Learning of Inflection and the Cell-Filling Problem
title_fullStr	Deep Learning of Inflection and the Cell-Filling Problem
title_full_unstemmed	Deep Learning of Inflection and the Cell-Filling Problem
title_sort	deep learning of inflection and the cell-filling problem
publisher	Accademia University Press
publishDate	2018
url	https://doaj.org/article/ea47fdee18ca49449c2938cac6bdd45f
work_keys_str_mv	AT francoalbertocardillo deeplearningofinflectionandthecellfillingproblem AT marcelloferro deeplearningofinflectionandthecellfillingproblem AT claudiamarzi deeplearningofinflectionandthecellfillingproblem AT vitopirrelli deeplearningofinflectionandthecellfillingproblem
_version_	1718397978786398208

Deep Learning of Inflection and the Cell-Filling Problem

Ejemplares similares