Computational Argumentation on the Web with Natural Language

Over the last four years, I have been working on topics related to computational argumentation on the web using natural language. Some of my publications and previous postings reflect these interests. Along with my colleague Tom van Engers, I prepared two research proposals on this topic, which are here presented as technical reports of our work. These reports are also relevant to the current IMPACT project, which addresses many of the same themes.
There is a short paper (five pages) which outlines key ideas, but has little in the way of discussion or background discussion. There is a long paper (28 pages) which goes into the proposal in much more depth.
Comments and discussion on these documents are very welcome.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

New Paper on Legal Case Factor Annotation and Extraction

Wim Peters and I have a paper which will appear in the proceedings of Semantic Processing of Legal Texts Workshop at the Language Resources and Evaluation Conference 2010. See the previous blog post about the workshop and the schedule.
Towards Annotating and Extracting Textual Legal Case Factors
Adam Wyner and Wim Peters
To appear in the Proceedings of Language Resources and Evaluation Conference 2010
Abstract
Case based reasoning is a crucial aspect of common law practice, where lawyers select precedent cases which they use to argue for or against a decision in a current case. To select the precedents, the relevant facts (the case factors) of precedent cases must be identified; the factors predispose the case decision for one side or the other. As the factors of cases are linguistically expressed, it is useful to provide a means to automate the identification of candidate passages. We outline and report the results of our approach to the identification of legal case factors which follows a bottom-up knowledge heavy strategy and uses the General Architecture for Text Engineering system. Salient lexical items are selected, concept classes of related terms are created, and annotation rules for simple and compound concepts are provided. The annotated concepts can be extracted from the cases, and cases can be classified with respect to the concepts. In addition to supporting extraction of relevant information, the approach has a didactic use in helping to train lawyers to perform close textual analysis. Finally, we carry out an initial collaborative, online annotation exercise using GATE TeamWare in order to develop a gold standard.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

Legal Case Ontology OWL file and Case Graphic

In conjunction with the paper by Rinke Hoekstra and I (as previously noted on this blog), we are making the ontology and a graphic of Popov v. Hayashi available:
Legal Case Ontology v9
This is the OWL file. It was developed using Protege version 4, a knowledge acquisition and editing tool.
As we have not previously made this a publicly available ontology, consider it a beta release. Comments very welcome.
The graphic is the ontological representation of Popov v. Hayashi; it is a pdf file.
Ontological Graphic for Popov v. Hayashi
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0