Pesquisa de Doutorado da Veronica

PREMISSAS (1) Pergunta potencialmente incompleta (OK) a) Qual capital Brasil?  graph query (?v1, capital de, Brasil) ... incompleta em relação ao contexto temporal e proveniência   b) Qual capital Brasil HOJE?  graph query id1 (?v1, capital de, Brasil), (id1, período, HOJE) ... completa em relação ao contexto temporal e incompleta em relação a proveniência   c) Qual capital Brasil HOJE de acordo com a Lei Federal?  graph query id1 (?v1, capital de, Brasil), (id1, período, HOJE), (id1, fonte, ?v2), (?v2, tipo, Lei Federal) ... completa em relação ao contexto temporal e a proveniência Abordagem:   Interagir em caso de pergunta incompleta? NÃO. O usuário pode ter assumido um contexto implícito e saberia completar caso questionado mas talvez nem o usuário saiba completar o contexto da pergunta (caso da Betina). Responder sem Interagir ( One-Shot/Stateless ), completar o Contexto que foi mapeado e fornecer uma ÚNICA resposta composta por todas as Alegações Contextualizadas que correspond

Link https://doi.org/10.1016/j.artint.2021.103627 Abstract This paper provides an extensive overview of the use of knowledge graphs in the context of Explainable Machine Learning . As of late, explainable AI has become a very active field of research by addressing the limitations of the latest machine learning solutions that often provide highly accurate, but hardly scrutable and interpretable decisions. An increasing interest has also been shown in the integration of Knowledge Representation techniques in Machine Learning applications, mostly motivated by the complementary strengths and weaknesses that could lead to a new generation of hybrid intelligent systems. Following this idea, we hypothesise that knowledge graphs, which naturally provide domain background knowledge in a machine-readable format, could be integrated in Explainable Machine Learning approaches to help them provide more meaningful, insightful and trustworthy explanations. 6. Current challenges (and ideas to

Trechos do texto da minha defesa de proposta In the Big Data era, the Veracity aspect explores data's consistency, accuracy, quality, and trustworthiness. Users must decide what is relevant or not, what is reliable, and which source of information they trust to consider the information accurate and helpful in carrying out the task he has in mind. [Professor Hermann comenta sobre modelos de reputação existentes]  But what do we mean by context? For this research, we adopted the general context definition from [Hogan et al., 2021]: “ By context, we herein refer to the scope of truth, and thus talk about the context in which some data are held to be true ”. [Professor Hermann indica uma referência sobre Truth da SEP ] Glanzberg, Michael, "Truth", The Stanford Encyclopedia of Philosophy (Summer 2021 Edition), Edward N. Zalta (ed.), URL = <https://plato.stanford.edu/archives/sum2021/entries/truth/>.  Information can be recorded through claims that represent what can b