Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/106161
Título: | Developing Amaia: A Conversational Agent for Helping Portuguese Entrepreneurs—An Extensive Exploration of Question-Matching Approaches for Portuguese | Autor: | Santos, José Duarte, Luís Ferreira, João Alves, Ana Oliveira, Hugo Gonçalo |
Palavras-chave: | semantic textual similarity; question answering; conversational agents; machine learning; information retrieval; text classification | Data: | 2020 | Editora: | MDPI | Projeto: | FCT’s INCoDe 2030 initiative, in the scope of the demonstration project AIA, “Apoio Inteligente a Empreendedores (chatbots)” | Título da revista, periódico, livro ou evento: | Information (Switzerland) | Volume: | 11 | Número: | 9 | Resumo: | This paper describes how we tackled the development of Amaia, a conversational agent for Portuguese entrepreneurs. After introducing the domain corpus used as Amaia’s Knowledge Base (KB), we make an extensive comparison of approaches for automatically matching user requests with Frequently Asked Questions (FAQs) in the KB, covering Information Retrieval (IR), approaches based on static and contextual word embeddings, and a model of Semantic Textual Similarity (STS) trained for Portuguese, which achieved the best performance. We further describe how we decreased the model’s complexity and improved scalability, with minimal impact on performance. In the end, Amaia combines an IR library and an STS model with reduced features. Towards a more human-like behavior, Amaia can also answer out-of-domain questions, based on a second corpus integrated in the KB. Such interactions are identified with a text classifier, also described in the paper. | URI: | https://hdl.handle.net/10316/106161 | ISSN: | 2078-2489 | DOI: | 10.3390/info11090428 | Direitos: | openAccess |
Aparece nas coleções: | I&D CISUC - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Developing-amaia-A-conversational-agent-for-helping-portuguese-entrepreneursan-extensive-exploration-of-questionmatching-approaches-for-portugueseInformation-Switzerland.pdf | 627.24 kB | Adobe PDF | Ver/Abrir |
Citações SCOPUSTM
3
Visto em 29/abr/2024
Citações WEB OF SCIENCETM
1
Visto em 2/mai/2024
Visualizações de página
55
Visto em 7/mai/2024
Downloads
18
Visto em 7/mai/2024
Google ScholarTM
Verificar
Altmetric
Altmetric
Este registo está protegido por Licença Creative Commons