Combining Text Mining and NLP for Information Retrieval

摘要

This paper presents an approach to automatic knowledge base construction used for automatic query expansion. We have designed a system that is able to gain domain knowledge from analysed texts. This system combines text mining and natural language processing to discover useful knowledge from large open-domain textual corpora. The Natural Language Processing extract noun phrases from texts. We have used a Data Mining technique called association rules. We show how this technique is able to discover knowledge about relations between noun phrases extracted from documents. We study how these relations can be used to improve retrieval performance in an Information Retrieval System (IRS). We report our experiments with the Amaryllis' project collections. Our results show that an increase in retrieval performance can be obtained using the association rules approach.