Multitask Learning with Deep Neural Networks for Community Question Answering

In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, whic...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Daniele Bonadiman, Antonio Uva, Alessandro Moschitti
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/70270dcef614458ea9deeac0dfdebc17
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:70270dcef614458ea9deeac0dfdebc17
record_format	dspace
spelling	oai:doaj.org-article:70270dcef614458ea9deeac0dfdebc172021-12-02T09:52:18ZMultitask Learning with Deep Neural Networks for Community Question Answering2499-455310.4000/ijcol.556https://doaj.org/article/70270dcef614458ea9deeac0dfdebc172017-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/556https://doaj.org/toc/2499-4553In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, which can exploit the previous two for achieving better results. Our DNN is trained jointly on all the three cQA tasks and learns to encode questions and comments into a single vector representation shared across the multiple tasks. The results on the official challenge test set show that our approach produces higher accuracy and faster convergence rates than the individual neural networks. Additionally, our method, which does not use any manual feature engineering, approaches the state of the art established with methods that make heavy use of it.Daniele BonadimanAntonio UvaAlessandro MoschittiAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 3, Iss 2, Pp 51-65 (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 Daniele Bonadiman Antonio Uva Alessandro Moschitti Multitask Learning with Deep Neural Networks for Community Question Answering
description	In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, which can exploit the previous two for achieving better results. Our DNN is trained jointly on all the three cQA tasks and learns to encode questions and comments into a single vector representation shared across the multiple tasks. The results on the official challenge test set show that our approach produces higher accuracy and faster convergence rates than the individual neural networks. Additionally, our method, which does not use any manual feature engineering, approaches the state of the art established with methods that make heavy use of it.
format	article
author	Daniele Bonadiman Antonio Uva Alessandro Moschitti
author_facet	Daniele Bonadiman Antonio Uva Alessandro Moschitti
author_sort	Daniele Bonadiman
title	Multitask Learning with Deep Neural Networks for Community Question Answering
title_short	Multitask Learning with Deep Neural Networks for Community Question Answering
title_full	Multitask Learning with Deep Neural Networks for Community Question Answering
title_fullStr	Multitask Learning with Deep Neural Networks for Community Question Answering
title_full_unstemmed	Multitask Learning with Deep Neural Networks for Community Question Answering
title_sort	multitask learning with deep neural networks for community question answering
publisher	Accademia University Press
publishDate	2017
url	https://doaj.org/article/70270dcef614458ea9deeac0dfdebc17
work_keys_str_mv	AT danielebonadiman multitasklearningwithdeepneuralnetworksforcommunityquestionanswering AT antoniouva multitasklearningwithdeepneuralnetworksforcommunityquestionanswering AT alessandromoschitti multitasklearningwithdeepneuralnetworksforcommunityquestionanswering
_version_	1718397951680708608

Multitask Learning with Deep Neural Networks for Community Question Answering

Ejemplares similares