Skip to Content

Project Archive

You will find in this section information about past research projects of the IRF and research partners.

Semantic Annotation for Patents

Professional patent researchers must look beyond keywords to find and analyse patents based on a sophisticated understanding of the patent’s content and meaning. Technologies to aid such searches with computer processing are at the cutting edge of information retrieval science.


Charting search in the patent space

The goal of this project was to develop a prototype that would help identifying documents obfuscated on purpose and discovering "sleeping members" of the patent corpus.


Multi-Threaded Extension of the IR Platform Terrier

A parallel implementation of the Information Retrieval toolkit Terrier on a high-performance computer in order to increase the efficiency of the search process in very large document collections was the aim of this project.


Detection of OCR Quality on Patents

The goal of this project was to identify a strategy for assessing the quality of a document obtained via an OCR process, and to assign a score (a quality coefficient) to each patent document.


Large Scale Logical Retrieval

This project was about enabling seamless searching over patents' full text and the aggregated information sources associated with the patent document.


FPGA for Information Retrieval

This project showed that the usage of FPGAs as "greener hardware" can deliver tremendous benefits by reducing the power consumed, while at the same time increasing the speed of execution.


Text Mining for Intellectual Property

The aim of the project was to provide a better means for modelling complex dependencies in patent texts and for searching patents using these dependencies.


Searching for Prior Art Patents

The goal of this project was to study automated methods for finding related patents based on a combination of many features extracted from the target patent.



The project goal was to extend the Information Retrieval toolkit, Lemur/Indri in such a way that it can be used with a super-computing infrastructure.