Automatic Evaluation Of Computer Science thesis Using Domain Ontology

Because of advanced in word process technologies, spell checking and grammar checks have become instant. Nonetheless, checking abstract errors from any given text has received little attention from similar researches. An example for abstract error is falsehood. The detection of abstract errors on any plain text is a challenging task for computers. Two of the major challenges are the unstructured nature of text documents and the lack of representation of common sense and domain specific knowledge in machine understandable format. Researches show that thousands of people are submitted thesis per annum in which many conceptual error due to technical errors. Technical errors are mainly caused by the omission of facts about the domain or subject. This paper analyses sample computer Science Thesis notes to find patterns that could be explored towards using information encoded in plain computer notes for the detection of conceptual errors. The paper proposes an ontology based architecture for a conceptual error detection system on computer notes.