68
Summarizing the Contents of a Research Paper using
Ontology based Concept Extraction
Juhi Moin, B. Saleena
School of Computing Science & Engineering
VIT University - Chennai Campus, Chennai, India
ABSTRACT
This paper proposes a new method to develop ontology based concept extraction approach for
summarizing the contents of a research paper, thereby helping the learners to quickly get an
outline of the research paper they want to read. The method adopted here for concept extraction is
a special mining method called, association rule mining. The technique employed for
summarization is keyword extraction. An ontology based concept extraction method is used to
extract concepts from the research paper which are relevant to the user’s requirement. Our
proposed idea is to give the learner a semantically defined and summarized description of the
research paper in the form of taxonomy. This approach saves the learner’s time in finding out the
relevant information in a given research paper.
Keywords: Association rule mining, Concept extraction, keyword extraction, Ontology.
1. INTRODUCTION
Selecting a research paper is a very important and continual activity in several organizations
similarly as in academic establishments. Since the volume of research paper is increasing day by
day, review of these papers have become now a difficult task. So as to mitigate this problem of
data overload, there requires some means of information reduction.
So as to get a desired paper of your interest it is essential that there ought to be an efficient manner
by which we can get an overall idea of the paper by simply gazing the summarized contents that
are obtained by extracting the most important ideas from the paper and herewith showing them to
the user.
It is clear that advantage exist behind extraction of ideas from the research paper. This paper
proposes a new method for performing this task based on association rule mining technique.
With the rapid growth of on-line data, it becomes more and more vital to seek out and describe
data effectively. To accomplish this we will use the semantic web mining techniques. Basically a
semantic web may be meshes of knowledge or information connected up in such a way that can be
simply process able by machines, on a worldwide scale. It is a vision of knowledge which will be
pronto understood by machines, therefore machines will perform additional of the tedious work
concerned with finding, combining, and acting upon data on the net.
Ontology refers to an information repository within which ideas and terms are defined as well as
relationships between those ideas are specified .Ontologies help us to describe about the specific
domain and can be used to reason about the concepts within that domain [8]. Semantic relations
are important associations between two or additional ideas, entities, or sets of entities [9].
International Journal of Research in Computer Applications & Information Technology
Volume 1, Issue 1, July-September, 2013, pp. 68-74, © IASTER 2013
www.iaster.com, ISSN Online: 2347-5099, Print: 2348-0009