I gave a tutorial on natural language processing for legal resource management at the International Conference on Legal Information Systems (JURIX) 2009 in Rotterdam, The Netherlands. The slides are available below. Comments welcome.
The following people attended:
- Andras Forhecz, Budapest University of Technology and Economics, Hungary
- Ales Gola, Ministry of Interior of Czech Republic
- Harold Hoffman, University Krems, Austria
- Czeslaw Jedrzejek, Poznan University of Technology, Poland
- Manuel Maarek, INRIA Grenoble, Rhone-Alpes
- Michael Sonntag, Johannes Kepler University Linz, Austria
- Vit Stastny, Ministry of Interior of Czech Republic
I thank the participants for their comments and look forward to continuing the discussions which we started in the tutorial.
At the link, one can find the slides. Comments are very welcome. The file is 2.2MB. The slides were originally prepared using Open Office’s Impress, then converted to PowerPoint.
Natural Language Processing Techniques for Managing Legal Resources on the Semantic Web
There is a bit more in the slides than was presented at the tutorial, covering in addition ontologies, parsers, and semantic interpreters.
In the coming weeks, I will make available additional detailed instructions as well as gazetteers and JAPE rules. I also plan to continue to add additional text mining materials.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0
Next week, 16 December 2009, I am giving a three hour tutorial at JURIX (International Conference on Legal Knowledge and Information Systems) in Rotterdam, The Netherlands on Natural Language Processing Techniques for Managing Legal Resources on the Semantic Web. The tutorial description appears below. Further material from the tutorial will be presented on the blog.
Legal resources such as legislation, public notices, and case law are increasingly available on the internet. To be automatically processed by web services, the resources must be annotated using semantic web technologies such as XML, RDF, and ontologies. However, manual annotation is labour and knowledge intensive. Using natural language processing techniques and systems (NLP), a significant portion of these resources can be automatically annotated. In this tutorial, we outline the motivations and objectives of NLP, give an overview of several accessible systems (General Architecture on Text Engineering, C&C/Boxer, Attempto Controlled English), provide examples of processing legal resources, and discuss future directions in this area.
I and my colleagues have a paper forthcoming in Semantic Processing of Legal Texts (S. Montemagni, D. Tiscornia, and E. Francesconi, eds.), Lecture Notes in Computer Science, Springer, 2009. Below please find a link to the paper and an abstract.
Approaches to text mining arguments from legal cases
University College London
Rachel Mochales-Palau and Marie-Francine Moens
Katholieke Universiteit Leuven
This paper describes recent approaches using text-mining to automatically profile and extract arguments from legal cases. We outline some of the background context and motivations. We then turn to consider issues related to the construction and composition of a corpora of legal cases. We show how a Context-Free Grammar can be used to extract arguments, and how ontologies and Natural Language Processing can identify complex information such as case factors and participant roles. Together the results bring us closer to automatic identification of legal arguments.