Machine Reading at Scale: A Search Engine for Scientific and Academic Research

Detalhes bibliográficos
Autor(a) principal: Sousa, Norberto
Data de Publicação: 2022
Outros Autores: Oliveira, Nuno, Praça, Isabel
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.22/21850
Resumo: The Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance.
id RCAP_d69216512eb5cfb4faaf86f0e726ede7
oai_identifier_str oai:recipp.ipp.pt:10400.22/21850
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Machine Reading at Scale: A Search Engine for Scientific and Academic ResearchNatural language processingDeep learningQuestion answering systemReading comprehensionInformation retrievaMachine reading at scaleThe Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance.This work has received funding from the following projects: UIDB/00760/2020 and UIDP/00760/2020.MDPIRepositório Científico do Instituto Politécnico do PortoSousa, NorbertoOliveira, NunoPraça, Isabel2023-01-25T11:33:03Z20222022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.22/21850eng10.3390/systems10020043info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-13T13:18:11Zoai:recipp.ipp.pt:10400.22/21850Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:41:56.142811Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Machine Reading at Scale: A Search Engine for Scientific and Academic Research
title Machine Reading at Scale: A Search Engine for Scientific and Academic Research
spellingShingle Machine Reading at Scale: A Search Engine for Scientific and Academic Research
Sousa, Norberto
Natural language processing
Deep learning
Question answering system
Reading comprehension
Information retrieva
Machine reading at scale
title_short Machine Reading at Scale: A Search Engine for Scientific and Academic Research
title_full Machine Reading at Scale: A Search Engine for Scientific and Academic Research
title_fullStr Machine Reading at Scale: A Search Engine for Scientific and Academic Research
title_full_unstemmed Machine Reading at Scale: A Search Engine for Scientific and Academic Research
title_sort Machine Reading at Scale: A Search Engine for Scientific and Academic Research
author Sousa, Norberto
author_facet Sousa, Norberto
Oliveira, Nuno
Praça, Isabel
author_role author
author2 Oliveira, Nuno
Praça, Isabel
author2_role author
author
dc.contributor.none.fl_str_mv Repositório Científico do Instituto Politécnico do Porto
dc.contributor.author.fl_str_mv Sousa, Norberto
Oliveira, Nuno
Praça, Isabel
dc.subject.por.fl_str_mv Natural language processing
Deep learning
Question answering system
Reading comprehension
Information retrieva
Machine reading at scale
topic Natural language processing
Deep learning
Question answering system
Reading comprehension
Information retrieva
Machine reading at scale
description The Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-01-01T00:00:00Z
2023-01-25T11:33:03Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.22/21850
url http://hdl.handle.net/10400.22/21850
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.3390/systems10020043
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799131506147328000