期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：10
出版社：Journal of Theoretical and Applied
摘要：In this paper, we present a new graph -based approach for keyphrases extraction using the pretopology theory. We formalize the notion of neighborhood to express different types of connections that may exist between the terms of a document. The first part of the proposed method consists in first selecting the keywords candidates using a pattern approach; the second part consists in detecting keywords as the most representative candidates by means of graph-based ranking algorithm using a pretopological formalism.
