Understanding natural language texts is a simple task for human beings, but despite recent advances, it is still a challenge for computational devices. An important step in allowing machines to understand texts in natural language is to annotate lexemes with semantic information. Semantic information has several levels and aspects, but a type of semantic annotation that has the ability to help determine the context of the statement is the ontological information. However, annotating texts according to an ontology is still a task that requires time and effort from annotators trained for this purpose. The goal of the project is to assist in the semantic enrichment of texts, through a rule-based annotator. Given an entry in the format required by the annotator, the tool returns a document annotated according to the concepts proposed by the SUMO ontology. The project consists in elaborating a semantic annotator based on rules that is able to annotate a corpus using the selected top-level ontologies.
展开▼
