Fuzzy Learning of Co-Similarities from Large-Scale Documents

Triadicdocument Co-Similarity Computing

In this work, we focus on the preprocessing step witch including data representation and similarity computing. It's proved that the sentence has been considered as a more informative feature term for improving the effectiveness of document clustering. While considering three levels (documents-sentences-words) to represent the data set, we are able to deal with a dependency between documents-sentences, as also between sentences-words and, by deduction, between documents-words.

The sentence-word-based document similarity (or triadic similarity) considers weighting scheme in computing the document similarity with sentences and the sentence similarity with words. A weighted value may be assigned as a link from a document to a word (or sentence) indicating the presence of the word(sentence) in that document.