期刊名称:International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN:2320-9798
电子版ISSN:2320-9801
出版年度:2015
卷号:3
期号:7
DOI:10.15680/ijircce.2015.0307145
出版社:S&S Publications
摘要:In comparison with hard clustering methods, in which a pattern belongs to a single cluster, fuzzyclustering algorithms allow patterns to belong to all clusters with differing degrees of membership. This work presentsa novel fuzzy clustering algorithm that operates on relational input data; i.e., data in the form of a square matrix ofpairwise similarities between data objects. The algorithm uses a graph representation of the data, and operates in anExpectation-Maximization framework in which the graph centrality of an object in the graph is interpreted as alikelihood. Results of applying the algorithm to sentence clustering tasks demonstrate that the algorithm is capable ofidentifying overlapping clusters of semantically related sentences, and that it is therefore of potential use in a variety oftext mining tasks. We also include results of applying the algorithm to benchmark data sets in several other domains
关键词:Fuzzy relational clustering; natural language processing; graph centrality