Cleyton Rodrigues

An Approach for Learning and Construction of Expressive Ontology from Text in Natural Language

In this paper, we present an approach based on Ontology Learning and Natural Language Processing for automatic construction of expressive Ontologies, specifically in OWL DL with ALC expressivity, from a natural language text. The viability of our approach is demonstrated through the generation of descriptions of complex axioms from concepts defined by users and glossaries found at Wikipedia. We evaluated our approach in an experiment with entry sentences enriched with hierarchy axioms, disjunction, conjunction, negation, as well as existential and universal quantification to impose restriction of properties. The obtained results prove that our model is an effective solution for knowledge representation and automatic construction of expressive Ontologies. Thereby, it assists professionals involved in processes for obtain, construct and model knowledge domain.

An ontological approach for simulating legal action in the Brazilian penal code

The applicability of Artificial Intelligence for the Legal Domain has several and non-depleted lines of research. Since Colonization, the use of ambiguity in drafting the Brazilian Legal Documents was a palliative to solve cases involving economic, political and social interests between local authorities with the European Court. Further, when conflicts between norms emerge, only time, specificity and superiority criteria are not enough to break the tie, a second degree level governing what criteria should be used in different situations need to be addressed as well. In face of these tangle legal documents, this research project aims to present the OntoCrime and OntoLegalTask: ontological representations through which one can formalize the Brazilian Penal Law to check norm violation and automate legal reasoning. Finally, an experiment with the drinking-drive law is presented.

Representing Knowledge in DL ALC from Text

Abstract In this paper, we present an approach based on Ontology Learning and Natural Language Processing for automatic construction of expressive Ontologies, specifically in OWL DL with ALC expressivity, from a natural language text. The viability of our approach is demonstrated through the generation of descriptions of complex axioms from concepts defined by users and glossaries found at Wikipedia. We evaluated our approach in an experiment with entry sentences enriched with hierarchy axioms, disjunction, conjunction, negation, as well as existential and universal quantification to impose restriction of properties. The obtained results prove that our model is an effective solution for knowledge representation and automatic construction of expressive Ontologies. Thereby, it assists professionals involved in processes for obtain, construct and model knowledge domain.

An autonomic multiagent system ontology-based for management of security of information

Computational security has become a worry among corporations. Indeed, the use if specific tools, procedures and policies that cover requirements to keep computation and IT infrastructure protected of malicious agents has been proved necessary. In order to address the problem of protecting computational resources, in this work we propose an autonomic model called AutoCore, constituted by a muilt-agent system, an intelligent interface (CoreEditor) and a formal ontologies (CoreSec). This proposal has been implemented, tested and validated in real scenarios to assist the safety activities and to minimize the administrator complexity.

An Ontology for Property Crime Based on Events from UFO-B Foundational Ontology

Property Crime has been highlighted as one of the major criminal offenses within the Brazilian Legal System. Moreover, it is common that there is some misunderstanding amongst the subtypes of this crime, such as Theft, Robbery, Misappropriation, and Extortion. We still emphasize the verynuance of legal literature that makes this domain as hostile as challenging: a weakly formalized knowledge, the presence of conflicts and ambiguities between norms, the heterogeneity of legal literature, as well as the diversity in reasoning models. Therefore, this article presents, inspired by UFO-B foundational ontology, a conceptual model for the representation of crimes against property in the Brazilian Criminal Code, in order to support some decision-making process, as the agents behavior classification and the inference of punishments. Thus, we present throughout this article, an ontological formalization for the Theory of Crime from Brazilian Penal Code, as well as for Property Crimes applications.

An Ontology Analysis Implementation in Constraint Logic Programming

Ontologies establish a common and unambiguous terminology for knowledge formal representation and (semi-) automatic reasoning, being gradually applied in Semantic Web services. OntoClean, on the other hand, is a methodology that addresses the creation of clean ontologies, i.e. the creation of taxonomic hierarchies to model properly the concepts in the domain of discourse. Due the lack of stable implementations in the literature, this paper presents an OntoClean implementation in Constraint Handling Rules (CHR), a Constraint Programming Prolog extension. Furthermore, it is proposed in an unprecedented way an evaluation for a Legal Ontology, highlighting the meta properties tagging for some domain concepts.

LSVF: a New Search Heuristic to Reduce the Backtracking Calls for Solving Constraint Satisfaction Problem

Many researchers in Artificial Intelligence seek for new algorithms to reduce the amount of memory/ time consumed for general searches in Constraint Satisfaction Problems. These improvements are accomplished by the use of heuristics which either prune useless tree search branches or even indicate the path to reach the (optimal) solution faster than the blind version of the search. Many heuristics were proposed in the literature, like the Least Constraining Value (LCV). In this paper we propose a new pre-processing search heuristic to reduce the amount of backtracking calls, namely the Least Suggested Value First: a solution whenever the LCV solely cannot measure how much a value is constrained. In this paper, we present a pedagogical example, as well as the preliminary results.

A proposal for an educational system service to support teaching/learning process for logic programming

Summary form only given. The interactive 3D technologies group at Microsoft Research Cambridge brings together research in vision, graphics, novel hardware and AR/VR. In this talk, Dr. Izadi will give a broad overview of his new group, highlighting a number of existing projects. The majority of the talk will focus on KinectFusion, a project that demonstrates the radically new user experiences that can be enabled when researching at the intersection of these different disciplines.

OntoPsic: Leveraging the Knowledge in the Treatment and Diagnosis of Telepsychiatry

Mental illness has always been target of debate and criticism by the society (modern or ancient). Several problems and challenges regarding Psychiatry, Telepsychiatry specifically are found in literature. The lack of information and the fear of the unknown have long been seen as a barrier for people with mental illness as well as all those involved in the process, such as family and the medical team. In the past, the lack of knowledge led the society to adopt harsh punishment for the patients, under the pretext that the same were possessed by some supernatural force. In this context, the lack of a public, formal and standardized model regarding any sort of information about this field was and remains as the central problem. Therefore, this paper proposes the OntoPsic, a domain-ontology for psychiatry applied to Healthcare Information System to define a common vocabulary about mental illness and Telepsychiatry. Besides relying on this base of knowledge to assist all involved in the treatment of mental disorders, this article also describes the OntoConsult, a system for the deduction of facts to support the decision making. In order to motivate the use of OntoPsic, the article reviews some applications and some practical results with the ontology.