VOX system: a semantic embodied conversational agent exploiting linked data

Abstract

In the last few years, the use of ontologies has spread thanks to the irruption of the Semantic Web. They have become a crucial tool in information systems as they explicitly state the meaning of information, making it possible to share it and to achieve higher levels of interoperability. However, being knowledge representation models as they are, other fields can take advantage of their characteristics to extend their capabilities. In particular, in the context of Embodied Conversational Agents, they can be used to provide them with semantic knowledge and, therefore, enhance their intellectual skills. In this paper, we propose an approach to explore the synergies between these technologies. Thus, we have developed a multimodal ECA that exploits the knowledge provided by the Linked Data initiative to help users in their search information tasks. Based on a semantic-guided keyword search, our approach is flexible enough to: 1) deal with different Linked Data repositories and 2) handle different search/knowledge domains in a multilingual way. To illustrate the potential of our approach, we have focused on the case of DBpedia, as it mirrors the information stored in the Wikipedia, providing a semantic entry to it.

Exploring the Relevance of Search Engines: An Overview of Google as a Case Study

“…This way, the inter-operability of digital resources through semantic models that classify them may be used based on related knowledge fields, using information visualization and classification methods like the ones defined by [12]. For this, the use and classification of educative repositories by related topics is proposed, so that a web of repositories with academic content and specialized according to the needs of users using tools previously mentioned like Linked Data [40], categorization or agent systems, will be available to implant new methods of search based on specialized search engines.…”

Uso de Ontologias para Agentes Conversacionais no Contexto de Ensino-Aprendizagem: Uma Revisão Sistemática da Literatura

“…A Tabela 6 apresenta os trabalhos classificados de acordo com os requisitos funcionais. [Freitas et al 2014], [Serón and Bobed 2016], [Lundqvist et al 2013] RF2 -Diferentes Métodos de Interação [Abdelkefi and Kallel 2016], [Hussain et al 2012], [Ong and Soriano 2014] RF3 -Afetividade [Ong and Soriano 2014], [Hussain et al 2012] Espera-se de um AC que este possa reagir com diferentes tipos de diálogos, portanto o domínio do conhecimento é importante e não deve ser limitado, principalmente quando se trata de uma arquitetura mais genérica e que será aplicada a diferentes situações. [Al-Zubaide and Issa 2011] apresenta o OntBot, um chatbot que tenta agir como humano na compreensão sobre o que o usuário fala, usando informações sobre o escopo da pergunta.…”

“…O OntBot se assemelha ao TempLang [Freitas et al 2014] que consegue responder a perguntas que exigem definições ou explicações e não se limita a um único domínio. Outro exemplo é o VOX System [Serón and Bobed 2016], um agente conversacional corporificado que por meio de gestos e interações permite fazer uma filtragem e uma busca do domínio que compete o diálogo. [Lundqvist et al 2013] desenvolveram um método para implementação de chatbots que podem mudar o conhecimento do domínio facilmente e expandir a base de conhecimento.…”

A Semantic Memory Bank Assisted by an Embodied Conversational Agents for Mobile Devices

“…Still, SLU is moving forward and new methods and applications are arising. Related to spoken language and natural interaction, Embodied Conversational Agents (ECA) [21] are graphical interfaces capable of using verbal and non-verbal modes of communication to interact with users in computer-based environments. ECAs have had a moderate widespread use (e.g.…”