Neural Question Generation

Question generation attempts to generate a natural language question given a passage and an answer. Most state-of-the-art methods have focused on generating simple questions involving single-hop relations and based on a single or a few sentences. In this project, we focus on generating multi-hop que...

Descripción completa

Detalles Bibliográficos
Autor: Urra Gorospe, Maite
Tipo de recurso: tesis de maestría
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/347190
Acceso en línea:https://hdl.handle.net/2117/347190
Access Level:acceso abierto
Palabra clave:Natural language processing (Computer science)
Neural networks (Computer science)
Deep Learning
Natural Language Processing
Question Generation
Tractament del llenguatge natural (Informàtica)
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Informàtica
id ES_6209cb603890c94dffd93b95ae70ca7d
oai_identifier_str oai:upcommons.upc.edu:2117/347190
network_acronym_str ES
network_name_str España
repository_id_str
spelling Neural Question GenerationUrra Gorospe, MaiteNatural language processing (Computer science)Neural networks (Computer science)Deep LearningNatural Language ProcessingQuestion GenerationTractament del llenguatge natural (Informàtica)Xarxes neuronals (Informàtica)Àrees temàtiques de la UPC::InformàticaQuestion generation attempts to generate a natural language question given a passage and an answer. Most state-of-the-art methods have focused on generating simple questions involving single-hop relations and based on a single or a few sentences. In this project, we focus on generating multi-hop questions which requires discovering and modeling the multiple entities and their semantic relations in the passage. To that end, we use the HotpotQA dataset, a multi-document and multi-hop dataset for questions answering that provides not only the context, question, and answer but also the supporting facts that lead to the answer. To solve the problem, we propose the use of transformer-based models, which have shown to perform well in single-hop question generation, and we study different variants to condition the model using the context and the supporting facts.Universitat Politècnica de CatalunyaBéjar Alonso, JavierLopez de Lacalle, Oier20212021-04-1820212021-06-11master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/347190reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3471902026-05-27T15:37:01Z
dc.title.none.fl_str_mv Neural Question Generation
title Neural Question Generation
spellingShingle Neural Question Generation
Urra Gorospe, Maite
Natural language processing (Computer science)
Neural networks (Computer science)
Deep Learning
Natural Language Processing
Question Generation
Tractament del llenguatge natural (Informàtica)
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Informàtica
title_short Neural Question Generation
title_full Neural Question Generation
title_fullStr Neural Question Generation
title_full_unstemmed Neural Question Generation
title_sort Neural Question Generation
dc.creator.none.fl_str_mv Urra Gorospe, Maite
author Urra Gorospe, Maite
author_facet Urra Gorospe, Maite
author_role author
dc.contributor.none.fl_str_mv Béjar Alonso, Javier
Lopez de Lacalle, Oier
dc.subject.none.fl_str_mv Natural language processing (Computer science)
Neural networks (Computer science)
Deep Learning
Natural Language Processing
Question Generation
Tractament del llenguatge natural (Informàtica)
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Informàtica
topic Natural language processing (Computer science)
Neural networks (Computer science)
Deep Learning
Natural Language Processing
Question Generation
Tractament del llenguatge natural (Informàtica)
Xarxes neuronals (Informàtica)
Àrees temàtiques de la UPC::Informàtica
description Question generation attempts to generate a natural language question given a passage and an answer. Most state-of-the-art methods have focused on generating simple questions involving single-hop relations and based on a single or a few sentences. In this project, we focus on generating multi-hop questions which requires discovering and modeling the multiple entities and their semantic relations in the passage. To that end, we use the HotpotQA dataset, a multi-document and multi-hop dataset for questions answering that provides not only the context, question, and answer but also the supporting facts that lead to the answer. To solve the problem, we propose the use of transformer-based models, which have shown to perform well in single-hop question generation, and we study different variants to condition the model using the context and the supporting facts.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-04-18
2021
2021-06-11
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/347190
url https://hdl.handle.net/2117/347190
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409465411829760
score 15,301603

Similares en LA Referencia