IRF Key Research Areas

The IRF focuses on large scale information retrieval and continuously evaluates its industrial relevance:

Automated annotation and information extraction

Relevant information is extracted from unstructured text and made available in the form of a database that bests suits specific needs.

Automated document categorization

We are developing a novel categorization method for documents that combines supervised machine learning and ontological reasoning, facilitating further processing and future search challenges.

Machine translation

Statistical machine translation (SMT) engines generate translations on the basis of statistical models derived from the analysis of bilingual text corpora. Although far from replacing human translations, SMT offers means to locate and identify potential strategic information in foreign language documents.

Image Retrieval in technical documents

The technique being developed enables efficient image searches (even when using only part of an image) for a variety of technical drawings, such as flow charts, block diagrams, time charts and graph plots.

Information Visualization

The IRF investigates the use of graphical representations and mapping techniques to provide intuitive views and interfaces to large data, thereby facilitating interpretation and analysis.

Interfaces and Workflows

One of our projects aims at translating extensive information search tasks that rely partly on complex search algorithms in an easy-to-use graphical interface based on the workflow paradigm. One of the benefits is the reusability of complicated search patterns by less experienced professionals.

Professional search

Another one of our projects consists in developing an integrated, online translation platform, where several human experts can take advantage of existing web-content and machine translation tools to collaboratively select and translate patents.