Web as Huge Information Source for Noun Phrases Integration in the Information Retrieval Process

Web is a rich and diversified source of information. In this article, we propose to benefit from this richness to collect and analyze documents, with the aim of a relational indexation based on noun phrases. Proposed data processing chain includes a spider collecting data to build textual corpora, and a linguistic module analyzing text to extract information. Comparison of obtained corpus with corpus from Amaryllis conference shows the linguistic diversity of collected corpora, and particularly the richness of extracted noun phrases.