Question Dependent Recurrent Entity Network for Question Answering

Question Answering is a task which requires building models capable of providing answers to questions expressed in human language. Full question answering involves some form of reasoning ability. We introduce a neural network architecture for this task, which is a form of Memory Network, that recogn...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Andrea Madotto, Giuseppe Attardi
Formato: article
Lenguaje:EN
Publicado: Accademia University Press 2017
Materias:
H
Acceso en línea:https://doaj.org/article/59faa4e5d27645598e4bb706792c2315
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:59faa4e5d27645598e4bb706792c2315
record_format dspace
spelling oai:doaj.org-article:59faa4e5d27645598e4bb706792c23152021-12-02T09:52:18ZQuestion Dependent Recurrent Entity Network for Question Answering2499-455310.4000/ijcol.547https://doaj.org/article/59faa4e5d27645598e4bb706792c23152017-12-01T00:00:00Zhttp://journals.openedition.org/ijcol/547https://doaj.org/toc/2499-4553Question Answering is a task which requires building models capable of providing answers to questions expressed in human language. Full question answering involves some form of reasoning ability. We introduce a neural network architecture for this task, which is a form of Memory Network, that recognizes entities and their relations to answers through a focus attention mechanism. Our model is named Question Dependent Recurrent Entity Network and extends the Recurrent Entity Network by exploiting aspects of the question during the memorization process. We validate the model on both synthetic and real datasets: the bAbI question answering dataset and the CNN & Daily News reading comprehension dataset. In our experiments, our models improved the existing Recurrent Entity Network and achieved competitive results in both dataset.Andrea MadottoGiuseppe AttardiAccademia University PressarticleSocial SciencesHComputational linguistics. Natural language processingP98-98.5ENIJCoL, Vol 3, Iss 2, Pp 11-22 (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
Andrea Madotto
Giuseppe Attardi
Question Dependent Recurrent Entity Network for Question Answering
description Question Answering is a task which requires building models capable of providing answers to questions expressed in human language. Full question answering involves some form of reasoning ability. We introduce a neural network architecture for this task, which is a form of Memory Network, that recognizes entities and their relations to answers through a focus attention mechanism. Our model is named Question Dependent Recurrent Entity Network and extends the Recurrent Entity Network by exploiting aspects of the question during the memorization process. We validate the model on both synthetic and real datasets: the bAbI question answering dataset and the CNN & Daily News reading comprehension dataset. In our experiments, our models improved the existing Recurrent Entity Network and achieved competitive results in both dataset.
format article
author Andrea Madotto
Giuseppe Attardi
author_facet Andrea Madotto
Giuseppe Attardi
author_sort Andrea Madotto
title Question Dependent Recurrent Entity Network for Question Answering
title_short Question Dependent Recurrent Entity Network for Question Answering
title_full Question Dependent Recurrent Entity Network for Question Answering
title_fullStr Question Dependent Recurrent Entity Network for Question Answering
title_full_unstemmed Question Dependent Recurrent Entity Network for Question Answering
title_sort question dependent recurrent entity network for question answering
publisher Accademia University Press
publishDate 2017
url https://doaj.org/article/59faa4e5d27645598e4bb706792c2315
work_keys_str_mv AT andreamadotto questiondependentrecurrententitynetworkforquestionanswering
AT giuseppeattardi questiondependentrecurrententitynetworkforquestionanswering
_version_ 1718397946598260736