A fuzzy set approach to extracting keywords from abstracts

An unsupervised keyword extraction method based on corpora is proposed. After representing each document in the collection by a fuzzy set of candidate keywords, the problem is translated into finding appropriate fuzzy membership degree for each candidate. In order to determine the membership degrees, first, all terms of the vocabulary are mapped into a two-dimensional space called class-collection map by obtaining two newly proposed fuzzy measures called fuzzy significance and fuzzy relevance for each term. At the second step, the mapped terms are grouped into three categories, namely, features, keywords and stopwords that are discriminated by their contribution to the meaning of the documents. Instead of a clustering approach for grouping purpose, a fuzzy rule base is provided. The method is independent of the language and data dimensionality. It does not require the use of dictionary, thesaurus nor natural language processing.