Construction of a disaster-support dynamic knowledge chatbot
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/22066 |
Resumo: | This dissertation is aimed at devising a disaster-support chatbot system with the capacity to enhance citizens and first responders’ resilience in disaster scenarios, by gathering and processing information from crowd-sensing sources, and informing its users with relevant knowledge about detected disasters, and how to deal with them. This system is composed of two artifacts that interact via a mediator graph-structured knowledge base. Our first artifact is a crowd-sourced disaster-related knowledge extraction system, which uses social media as a means to exploit humans behaving as sensors. It consists in a pipeline of natural language processing (NLP) tools, and a mixture of convolutional neural networks (CNNs) and lexicon-based models for classifying and extracting disasters. It then outputs the extracted information to the knowledge graph (KG), for presenting connected insights. The second artifact, the disaster-support chatbot, uses a state-of-the-art Dual Intent Entity Transformer (DIET) architecture to classify user intents, and makes use of several dialogue policies for managing user conversations, as well as storing relevant information to be used in further dialogue turns. To generate responses, the chatbot uses local and official disaster-related knowledge, and infers the knowledge graph for dynamic knowledge extracted by the first artifact. According to the achieved results, our devised system is on par with the state-of-the- art on Disaster Extraction systems. Both artifacts have also been validated by field specialists, who have considered them to be valuable assets in disaster-management. |
id |
RCAP_6f15392aec9c919dd3e9eac881ccc3ea |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/22066 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Construction of a disaster-support dynamic knowledge chatbotDisaster-managementNatural language processingArtificial intelligenceMachine learningChatbotsGraph databasesGestão de desastresProcessamento da língua naturalInteligência artificialAprendizagem automáticaBases de dados em grafosThis dissertation is aimed at devising a disaster-support chatbot system with the capacity to enhance citizens and first responders’ resilience in disaster scenarios, by gathering and processing information from crowd-sensing sources, and informing its users with relevant knowledge about detected disasters, and how to deal with them. This system is composed of two artifacts that interact via a mediator graph-structured knowledge base. Our first artifact is a crowd-sourced disaster-related knowledge extraction system, which uses social media as a means to exploit humans behaving as sensors. It consists in a pipeline of natural language processing (NLP) tools, and a mixture of convolutional neural networks (CNNs) and lexicon-based models for classifying and extracting disasters. It then outputs the extracted information to the knowledge graph (KG), for presenting connected insights. The second artifact, the disaster-support chatbot, uses a state-of-the-art Dual Intent Entity Transformer (DIET) architecture to classify user intents, and makes use of several dialogue policies for managing user conversations, as well as storing relevant information to be used in further dialogue turns. To generate responses, the chatbot uses local and official disaster-related knowledge, and infers the knowledge graph for dynamic knowledge extracted by the first artifact. According to the achieved results, our devised system is on par with the state-of-the- art on Disaster Extraction systems. Both artifacts have also been validated by field specialists, who have considered them to be valuable assets in disaster-management.Esta dissertação visa a conceção de um sistema de chatbot de apoio a desastres, com a capacidade de aumentar a resiliência dos cidadãos e socorristas nestes cenários, através da recolha e processamento de informação de fontes de crowdsensing, e informar os seus utilizadores com conhecimentos relevantes sobre os desastres detetados, e como lidar com eles. Este sistema é composto por dois artefactos que interagem através de uma base de conhecimento baseada em grafos. O primeiro artefacto é um sistema de extração de conhecimento relacionado com desastres, que utiliza redes sociais como forma de explorar o conceito humans as sensors. Este artefacto consiste numa sequência de ferramentas de processamento de língua natural, e uma mistura de redes neuronais convolucionais e modelos baseados em léxicos, para classificar e extrair informação sobre desastres. A informação extraída é então passada para o grafo de conhecimento. O segundo artefacto, o chatbot de apoio a desastres, utiliza uma arquitetura Dual Intent Entity Transformer (DIET) para classificar as intenções dos utilizadores, e faz uso de várias políticas de diálogo para gerir as conversas, bem como armazenar informação chave. Para gerar respostas, o chatbot utiliza conhecimento local relacionado com desastres, e infere o grafo de conhecimento para extrair o conhecimento inserido pelo primeiro artefacto. De acordo com os resultados alcançados, o nosso sistema está ao nível do estado da arte em sistemas de extração de informação sobre desastres. Ambos os artefactos foram também validados por especialistas da área, e considerados um contributo significativo na gestão de desastres.2021-12-23T00:00:00Z2020-12-23T00:00:00Z2020-12-232020-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10071/22066TID:202627489engBoné, João Miguel Baptistainfo: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:RCAAP2023-11-09T17:30:03Zoai:repositorio.iscte-iul.pt:10071/22066Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:13:29.420941Repositório 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 |
Construction of a disaster-support dynamic knowledge chatbot |
title |
Construction of a disaster-support dynamic knowledge chatbot |
spellingShingle |
Construction of a disaster-support dynamic knowledge chatbot Boné, João Miguel Baptista Disaster-management Natural language processing Artificial intelligence Machine learning Chatbots Graph databases Gestão de desastres Processamento da língua natural Inteligência artificial Aprendizagem automática Bases de dados em grafos |
title_short |
Construction of a disaster-support dynamic knowledge chatbot |
title_full |
Construction of a disaster-support dynamic knowledge chatbot |
title_fullStr |
Construction of a disaster-support dynamic knowledge chatbot |
title_full_unstemmed |
Construction of a disaster-support dynamic knowledge chatbot |
title_sort |
Construction of a disaster-support dynamic knowledge chatbot |
author |
Boné, João Miguel Baptista |
author_facet |
Boné, João Miguel Baptista |
author_role |
author |
dc.contributor.author.fl_str_mv |
Boné, João Miguel Baptista |
dc.subject.por.fl_str_mv |
Disaster-management Natural language processing Artificial intelligence Machine learning Chatbots Graph databases Gestão de desastres Processamento da língua natural Inteligência artificial Aprendizagem automática Bases de dados em grafos |
topic |
Disaster-management Natural language processing Artificial intelligence Machine learning Chatbots Graph databases Gestão de desastres Processamento da língua natural Inteligência artificial Aprendizagem automática Bases de dados em grafos |
description |
This dissertation is aimed at devising a disaster-support chatbot system with the capacity to enhance citizens and first responders’ resilience in disaster scenarios, by gathering and processing information from crowd-sensing sources, and informing its users with relevant knowledge about detected disasters, and how to deal with them. This system is composed of two artifacts that interact via a mediator graph-structured knowledge base. Our first artifact is a crowd-sourced disaster-related knowledge extraction system, which uses social media as a means to exploit humans behaving as sensors. It consists in a pipeline of natural language processing (NLP) tools, and a mixture of convolutional neural networks (CNNs) and lexicon-based models for classifying and extracting disasters. It then outputs the extracted information to the knowledge graph (KG), for presenting connected insights. The second artifact, the disaster-support chatbot, uses a state-of-the-art Dual Intent Entity Transformer (DIET) architecture to classify user intents, and makes use of several dialogue policies for managing user conversations, as well as storing relevant information to be used in further dialogue turns. To generate responses, the chatbot uses local and official disaster-related knowledge, and infers the knowledge graph for dynamic knowledge extracted by the first artifact. According to the achieved results, our devised system is on par with the state-of-the- art on Disaster Extraction systems. Both artifacts have also been validated by field specialists, who have considered them to be valuable assets in disaster-management. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-23T00:00:00Z 2020-12-23 2020-10 2021-12-23T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10071/22066 TID:202627489 |
url |
http://hdl.handle.net/10071/22066 |
identifier_str_mv |
TID:202627489 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
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.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_ |
1799134691278716928 |