Study of Learning Source Ontology Modeling in Remote Education

2018

RCS

Resumen. El proceso de aprendizaje de ontologías comprende tres pasos fundamentales: creación de clases y relaciones, población y evaluación. Este documento se enfoca en la creación de clases y relaciones, realizando un estudio sobre la detección de subclases para la ontología. Como caso de estudio se seleccionó un dominio pedagógico, donde se construyó un corpus semiautomático, a partir de artículos escritos en español publicados en el área de Ciencias Sociales. Para la detección de subclases fueron implementadas cuatro métricas de similitud textual basadas en términos, con las cuáles se construyó una heurística para determinar cuáles de los conceptos tienen posibilidades de convertirse en una subclase de la ontología y tienen una relación taxonómica con la clase principal. La evaluación se realizó mediante un gold vericado por un experto en el dominio y el contexto teórico de las clases y se obtuvo el recuerdo de cada clase. Los resultados muestran un recuerdo de 100 % 72 % y 67 % respectivamente para cada una de las clases, además de que se recuperaron conceptos relacionados a la clase principal mediante relaciones no taxonómicas.

Section: Trabajos Relacionadosunclassified

Identificación de relaciones taxonómicas de dominio usando métricas textuales

Alemán¹,

Somodevilla²,

2018

RCS

“…In both works is defined an ontology for each entity in the learning process, and the evaluation is conducted with a manual process supervised for domain experts. Other researchers are focused on online education ( [20], [2], [21] and recently [26]) where ontologies are manually defined from XML resources available in the Internet, and the evaluation is a manual process too. An ontology created from CASE diagrams for on-line education is presented in [22]; its evaluation is addressed by experts in a manual process.…”

Section: Ontology Creationmentioning

confidence: 99%

“…Ontologies can be used for purposes such as structure knowledge in taxonomies, vocabulary manage, natural language processing applications, searches, recommendation systems, and e-learning among others [2,3,4]. Ontologies can model interaction systems between users and their environment, since to its property to manage complex knowledge in reusable formal representations.…”

Section: Introductionmentioning

confidence: 99%

A Proposal for Domain Ontological Learning

Alemán¹,

Somodevilla²,

2017

RCS

In this paper, the population ontology problem is addressed and a semiautomatic methodology for ontology learning is proposed. In this work a study of advances in this research area is presented, which is divided according with the aim of the ontology and the class extraction, creation, or population. Based on this study, an initial proposal for ontology semiautomatic population is introduced. This initial proposal consists of four general steps: class extraction, creation, population and evaluation, where the population step is the main objective of this research. As future work, this methodology is intended to be applied to pedagogic domain, specially to classroom learning tools.

“…In both works is dened an ontology for each entity in the learning process, and the evaluation is conducted with a manual process supervised for domain experts. Other researchers are focused on online education ( [21,3,4] and recently [12]) where ontologies are manually dened from XML resources available in the Internet, and the evaluation is a manual process too. An ontology created from CASE diagrams for on-line education is presented in [2]; its evaluation is addressed by experts in a manual process.…”

Section: Related Workmentioning

confidence: 99%

A Semantic Proposal for Semiautomatic Corpus Creation in the Pedagogic Domain

Alemán¹,

Somodevilla-García²,

2017

RCS

In this research is introduced a methodology for the ontology automatic construction for the pedagogical domain based on the denition of two lexical resources: a domain corpus and, the use of a domain dictionary. In this research, the pedagogical corpus was building manually, where aspects such as learning strategies, intelligences types and learning styles were included. After that, the corpus is processed for extracting a list of concepts linked to the domain predened classes. Each concept is searched in ve dictionaries, including synonyms. This process is automatically performed, removing close words, words with low frequency. As result of this process, is building a domain dictionary which include concepts related with each domain class. The preliminary results show an anity between the corpus and the dictionary, which is a very important resource for an ontology denition process. As future work, these resources will be used for detect classes in a ontology learning process for the pedagogical domain using machine learning techniques.