RICSH
RICSH (contextual information retrieval by thematic segmentation of documents) is a software platform for preprocessing textual documents and integrating them in a warehouse. RICSH is composed of two modules: a module for identifying and extracting thematic units for each textual document; and a module for information retrieval that allows, given a query, finding the most relevant documents in a text corpus, taking both user and query profiles into account.
RICSH screenshot