Home // eKNOW 2012, The Fourth International Conference on Information, Process, and Knowledge Management // View article

A Context-Aware Framework for Semantic Indexing of Research Papers

Authors:
Maryam Tayefeh Mahmoudi
Fattaneh Taghiyareh
Koushyar Rajavi
Mohammad Saleh Pirouzi

Keywords: Indexing; domain ontology; research paper; WordNet; incremental learning.

Abstract:
Automatic indexing and annotation of publications have a significant role in retrieving and processing required papers from the massive amount of existing papers in the databases. In this paper, a framework for indexing research papers based on domain ontology is represented. The domain ontology, which is constructed for this purpose, is on agent science and technology. The initial step to indexing is to recognize the major concerns and the basic constituents in the title of papers, which has been accomplished through proposing a few NLP-based rules. To annotate each paper, the mentioned ontology and WordNet are employed. Experimental results on about 155 research papers lead us to estimate that our framework is capable of semantic indexing in about 80 percent of the situations. Since we have considered the ontology separately from the constituents of the whole system, the proposed framework is domain-independent and can be applied to any other domain ontology.

Pages: 116 to 121

Copyright: Copyright (c) IARIA, 2012

Publication date: January 30, 2012

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-181-6

Location: Valencia, Spain

Dates: from January 30, 2012 to February 4, 2012