Project Description

Summary

The judiciary is faced with enormous case loads. Therefore, alternative dispute resolution mechanisms such as mediation are very welcome. The legal domain of this project is damages disputes, which concerns a substantial number of the court cases. A decision to either go to court or to mediate is ideally based on a well-informed choice. Currently the necessary information to make such a decision is often lacking. One of the aims of this project is to provide litigants with information about the expected outcome of a court proceedings, in legal negotiation literature called a BATNA. This information will be provided through intelligent disclosure of case-law using Semantic Web technology. The problem of finding relevant case-law in order to determine a BATNA can be reduced to the problem of finding closely related documents in a large, semi-structured collection. The paradigm of ontology-based search and navigation is particularly well-suited in cases where the application domain is sufficiently well structured, and where user-queries need substantial amounts of refinement, typically in an interactive dialogue with a system. Members of the proposing team have substantial experience in building such interfaces. The legal domain in general, and damage-case BATNA determination specifically poses a significant challenge beyond the state of the art in ontology-based search interfaces. The project team consist of members of the AI department and the Law faculty of the Vrije Universiteit Amsterdam.

Aim

Both proponents and opponents of mediation agree that a decision to either go to court or to mediate (or negotiate, arbitrate) should be based on a well-informed choice. Currently the necessary information to make such a decision is often lacking. One of the aims of this project is to provide litigants with information about the expected outcome of a court proceedings.

In literature as well as practice of Alternative Dispute Resolution the Harvard method is influential. It is based on work carried out in the setting of the so-called PON: the Project on Negotiation. This Harvard Negotiation Project, currently headed by Robert Mnookin, introduced the concept of principled negotiation, which advocates separating the problem from the people [Fisher and Ury 1981]. Fundamental to the concept of principled negotiation is the notion of Know your best alternative to a negotiated agreement (BATNA). The reason you negotiate with someone is to produce better results than would otherwise occur. If you are unaware of what results you could obtain if the negotiations are unsuccessful, you run the risk of:

  1. Entering into an agreement that you would be better off rejecting; or
  2. Rejecting an agreement you would be better off entering into.

The proposed project aims at facilitating the establishment of a BATNA through intelligent disclosure of case-law. The legal domain we are looking at is damages disputes. Two questions are relevant here. First, damages are compensated only if the other party can be held liable. Whether this is the case depends on a number of factors such as the probability of the occurred event and the nature of the damages. Once a (legal) person can be held liable, the second question is what compensation is reasonable. Both answers are relevant for determining a BATNA in damages disputes.

A BATNA is relevant for parties engaged in a mediation. For them this information helps to decide during mediation whether or not to proceed. Knowing one's BATNA is, however, in particular important for parties on the point of deciding what process to enter into, what dispute resolution process is most effective for them. Lodder & Zeleznikow propose in their forthcoming contribution to the Harvard Negotiation Law Review a 'Three Step Model for Online Dispute Resolution' (ODR). ODR can be defined as any form of dispute resolution in which wholly or partially the internet is designated as the virtual location to solve a dispute. The first step in this model is the determination of a BATNA. Split-Up is a system that shows both litigants what they would be expected to be awarded by a court if their relative claims were accepted. The difficulty with systems like Split-Up is how to obtain the information regarding the BATNA's, and in particular how to keep this information up-to-date. This project delivers software that helps determining one's BATNA on the basis of a regularly updated set of documents, i.e. the relevant case law.

The pubic available site www.rechtspraak.nl has been online since the end of 1999, and has become a valuable source for most practising lawyers as well as academics. Whether a case is published on the site is determined on the basis of a list of criteria. The intranet of the judiciary (Porta Iuris), on the other hand, provides all electronically available cases, and we hope to get access to this document set for this research.

Approach

In Computer Science terms, the problem of finding relevant case-law in order to determine a BATNA can be reduced to the problem of finding closely related documents in a large, semistructured collection. Computer Science has developed a number of techniques for this problem, ranging from "knowledge free" techniques based on shallow text-parsing and statistical analysis to "knowledge intensive" methods, such as ontology-based search and navigation.

The paradigm of ontology-based search and navigation is particularly well-suited in cases where the application domain is sufficiently well structured, and where user-queries need substantial amounts of refinement, typically in an interactive dialogue with a system. The ontology serves multiple purposes for search and navigation in the document set:

  1. To disambiguate search terms;
  2. To semantically narrow or broaden searches when too many or too few results are returned;
  3. To suggest semantically related queries that involve syntactically different terms.

Each of these points contribute to an interactive exploration interface where the classical distinction between searching (starting from a precise query) and browsing (undirected navigation through the document set) disappears.