Text mining is an important field because of the necessity of obtaining knowledge from the enormous number of text documents. This system describes text mining technique for automatically extracting association rules amongst keywords from collections of textual documents. This system integrates XML technology with Information Retrieval scheme (TF-IDF) for keyword selection that automatically selects the most discriminative keywords for use in association rules generation and uses data mining technique for association rules discovery. This system consists of text preprocessing phase for filtration and indexing of the document, knowledge distillation phase for generating association rules by using GARW algorithm and visualisation phase for displaying results. This system extracts association rules that contain important features and describe the informative news (knowledge) that are included in the XML documents collection by using generated association rules. This system is implemented by using C# programming language.