Computer Aided Document Indexing for Accessing Legislation

CADIAL addressed the challenges of semantic indexing and retrieval of Croatian legislative documents. Within this projects, we developed an indexer with the terms from the EuroVoc thesuarus and an efficient semantic search engine that leverages this semantic information. The CADIAL search engine is now widely used on a daily basis.

Description

Large amounts of legislative documents such as laws and regulations are now available in digital form. Since legislation is continually being revised, the amount of documents rises rapidly. Moreover, with time some regulations and laws become invalid, but should nonetheless remain available for reference. The goal of the CADIAL (Computer Aided Document Indexing for Accessing Legislation) project was to develop and deploy a search engine for Croatian legislation that would allow for semantic search over documents indexed by the Eurovoc theusarus. The project was jointly supported by the Government of Flanders (under the grant KRO/009/06) and the Ministry of Science, Education and Sports of the Republic of Croatia.

The CADIAL project was awarded the Prime Minister Award for special achievements in the field of e-Government. It is the first system that implements Eurovoc thesaurus for structuring and retrieval of legislative documents in Croatian. The CADIAL search engine was also awarded the renowned VIDI e-novation award 2009 “Golden Tesla’s egg” for the best innovative ICT solution in the category of academic institutions.

Summary of the project results

The CADIAL project was successfully finished in September 2009, with the following main deliverables:

  • The complete database of the 20.000 legal documents of the Republic of the Croatia indexed with descriptors from the Eurovoc thesaurus;
  • Publicly accessible CADIAL search engine (cadial.hidra.hr) that operates on that database (see CADIAL leaflet);
  • The book Technologies for the Processing and Retrieval of Semi-Structured Documents that summarizes the research work carried out within the framework of the CADIAL project and the implementations of the research results;
  • A number of publications: journal and conference papers, invited lectures, book chapters, and the book (for a detailed list see Project Publications);
  • eCADIS system for automatic document indexing with descriptors from Eurovoc thesaurus (for more details see Project Results).

The promotion of the CADIAL project results was held at Croatian Journalists’ Association conference hall in Zagreb on November 11, 2009. Click here to read more about this event.

Project fact sheet

Participants: Digital Information Documentation Office of the Government of the Republic of Croatia (formerly Croatian Information Documentation Referral Agency), TakeLab FER
Sponsors: Government of Flanders (under the grant KRO/009/06); Ministry of Science, Education and Sports of the Republic of Croatia
Project coordinators:

  • Promotor: Prof. Marie-Francine Moens, Department of Computer Science, Katholieke Universiteit Leuven, Belgium
  • Partner: Prof. Bojana Dalbelo Bašić, Faculty of Electrical Engineering and Computing (FER), University of Zagreb, Croatia

Duration: March 1, 2007 – September 15, 2009

Learn more about the project from the official project website.