Towards an open question answering architecture

Abstract

Billions of facts pertaining to a multitude of domains are now availableon the Web as RDF data. However, accessing this data is stilla difficult endeavour for non-expert users. In order to melioratethe access to this data, approaches imposing minimal hurdles totheir users are required. Although many question answering systemsover Linked Data have being proposed, retrieving the desireddata is still significantly challenging. In addition, developing andevaluating question answering systems remains a very complex task.To overcome these obstacles, we present a modular and extensibleopen-source question answering framework. We demonstratehow the framework can be used by integrating two state-of-the-artquestion answering systems. As a result our evaluation shows thatoverall better results can be achieved by the use of combinationrather than individual stand-alone versions

Uma Abordagem para Identificação de Similaridade Entre Recursos Educacionais Utilizando Bases de Conhecimento Externas

“…Bizer, Heath, e Berners-Lee (2009) relatam que os dados ligados é um modo de organizar a web criando relações de acordo com o tipo de dado. Segundo Marx et al (2014), dados ligados são fundamentais para agregar valor ao conjunto de dados original enriquecendo-o com associações a outros conjuntos de dados conexos. Neste sentido, a DBpedia 5 , projeto que extrai conhecimento estruturado, multilíngue da Wikipedia, destaca-se como uma das fontes de conhecimento mais populares e amplamente utilizada para consultas a dados ligados.…”

Trill: A Reusable Front-End for QA Systems

“…To achieve the modularity by making the front-end independent from the back-end of the QA system, we build Trill on top of a framework that provides a reusable architecture for QA systems. We are aware of four such architectures namely: QALL-ME [6], openQA [7], the Open KnowledgeBase and Question-Answering (OKBQA) challenge 7 and Qanary [9,1,4]. We choose to build Trill on top of the last mentioned framework, Qanary, since it allows the highest flexibility to integrate new QA components.…”

Introducing Feedback in Qanary: How Users Can Interact with QA Systems

“…Besides Qanary, three frameworks tried to achieve this goal: QALL-ME [6], openQA [9] and the Open Knowledge Base and Question-Answering (OKBQA) challenge (cf., http://www.okbqa.org/). To the best of our knowledge these frameworks do not address the problem of integrating user interaction.…”