Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning

In this paper, we propose a Deep Learning architecture for several Italian Natural Language Processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture provided state of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pierpaolo Basile, Pierluigi Cassotti, Lucia Siciliani, Giovanni Semeraro
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/7d12c46b5d31477aacc399f811980343
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7d12c46b5d31477aacc399f811980343
record_format	dspace
spelling	oai:doaj.org-article:7d12c46b5d31477aacc399f8119803432021-12-02T09:52:19ZBi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning2499-455310.4000/ijcol.553https://doaj.org/article/7d12c46b5d31477aacc399f8119803432017-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/553https://doaj.org/toc/2499-4553In this paper, we propose a Deep Learning architecture for several Italian Natural Language Processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture provided state of the art performance in several sequence labeling tasks for the English language. We exploit the same approach for the Italian language and extend it for performing a multi-task learning involving PoS-tagging and sentiment analysis. Results show that the system is able to achieve state of the art performance in all the tasks and in some cases overcomes the best systems previously developed for the Italian.Pierpaolo BasilePierluigi CassottiLucia SicilianiGiovanni SemeraroAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 3, Iss 2, Pp 37-50 (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 Pierpaolo Basile Pierluigi Cassotti Lucia Siciliani Giovanni Semeraro Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
description	In this paper, we propose a Deep Learning architecture for several Italian Natural Language Processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. This architecture provided state of the art performance in several sequence labeling tasks for the English language. We exploit the same approach for the Italian language and extend it for performing a multi-task learning involving PoS-tagging and sentiment analysis. Results show that the system is able to achieve state of the art performance in all the tasks and in some cases overcomes the best systems previously developed for the Italian.
format	article
author	Pierpaolo Basile Pierluigi Cassotti Lucia Siciliani Giovanni Semeraro
author_facet	Pierpaolo Basile Pierluigi Cassotti Lucia Siciliani Giovanni Semeraro
author_sort	Pierpaolo Basile
title	Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
title_short	Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
title_full	Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
title_fullStr	Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
title_full_unstemmed	Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning
title_sort	bi-directional lstm-cnns-crf for italian sequence labeling and multi-task learning
publisher	Accademia University Press
publishDate	2017
url	https://doaj.org/article/7d12c46b5d31477aacc399f811980343
work_keys_str_mv	AT pierpaolobasile bidirectionallstmcnnscrfforitaliansequencelabelingandmultitasklearning AT pierluigicassotti bidirectionallstmcnnscrfforitaliansequencelabelingandmultitasklearning AT luciasiciliani bidirectionallstmcnnscrfforitaliansequencelabelingandmultitasklearning AT giovannisemeraro bidirectionallstmcnnscrfforitaliansequencelabelingandmultitasklearning
_version_	1718397954028470272

Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning

Ejemplares similares