Enriching legal text corpora with ontologies. An option for higher pricing of legal information systems?
Erich Schweighofer
University of Vienna, Center for Computers and Law
Erich.Schweighofer@univie.ac.at
http://rechtsinformatik.univie.ac.at
In recent years, basic legal information has become freely available on the Web. Governments, parliaments, courts but also private initiatives like those of the World Legal Information Institute (WorldLII) consortium have greatly invested in providing this public service. Document delivery, once a major service, has moved to a niche market depending of other advantages like easer manageability. Responding to this development, legal information providers have added electronic handbooks and commentaries to its services.
Legal ontologies are not that new to information retrieval. Thesauri, citations, classifications etc. were and are part of meta data of legal text corpora but not that widely used. However, the increasing quantity of legal knowledge requires more advanced searching techniques then full text retrieval. Intelligent tools with value-added information may be a solution, based on one decade of research on legal ontologies. (Semi)automatic categorization and document analysis will play a decisive factor for linking text corpora with legal ontologies.
Real-time analysis of text corpora offers the option of a dynamic legal commentary. Documents can be searched by conceptual structures. Relevance assessment and browsing are facilitated by summarization tools. Multilingual information retrieval allows access to other jurisdictions.
Such a dynamic information delivery service seems to be a successful business model for efficient support of legal knowledge management. Decisive factors are the quality of the meta data and real-time information but also more efficient legal services and cost savings.
