Papers in JURIX 2013

I’m co-author of two papers at The 26th International Conference on Legal Knowledge and Information Systems (JURIX 2013), Bologna, Italy.
Bologna.  Food.
Argumentation Schemes for Reasoning about Factors with Dimensions
Katie Atkinson, Trevor Bench-Capon, Henry Prakken, and Adam Wyner
In previous work we presented argumentation schemes to capture the CATO and value based theory construction approaches to reasoning with legal cases with factors. We formalised the schemes with ASPIC+, a formal representation of instantiated argumentation. In ASPIC+ the premises of a scheme may either be a factor provided in a knowledge base or established using a further argumentation scheme. Thus far we have taken the factors associated with cases to be given in the knowledge base. While this is adequate for expressing factor based reasoning, we can further investigate the justifications for the relationship between factors and facts or evidence. In this paper we examine how dimensions as used in the HYPO system can provide grounds on which to argue about which factors should apply to a case. By making this element of the reasoning explicit and subject to argument, we advance our overall account of reasoning with legal cases and make it more robust.
author = {Katie Atkinson and Bench-Capon, Trevor and Henry Prakken and Adam Wyner},
title = {Argumentation Schemes for Reasoning about Factors with Dimensions},
booktitle = {Proceedings of 26th International Conference on Legal Knowledge and Information Systems (JURIX 2013)},
year = {2013},
pages = {??-??},
address = {Amsterdam},
publisher = {IOS Press}
A Case Study on Legal Case Annotation
Adam Wyner, Wim Peters, and Daniel Katz
The paper reports the outcomes of a study with law school students to annotate a corpus of legal cases for a variety of annotation types, e.g. citation indices, legal facts, rationale, judgement, cause of action, and others. An online tool is used by a group of annotators that results in an annotated corpus. Differences amongst the annotations are curated, producing a gold standard corpus of annotated texts. The annotations can be extracted with semantic searches of complex queries. There would be many such uses for the development and analysis of such a corpus for both legal education and legal research.
author = {Adam Wyner and Peters, Wim, and Daniel Katz},
title = {A Case Study on Legal Case Annotation},
booktitle = {Proceedings of 26th International Conference on Legal Knowledge and Information Systems (JURIX 2013)},
year = {2013},
pages = {??-??},
address = {Amsterdam},
publisher = {IOS Press}
Shortlink to this page.
By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

ICAIL 2013 Papers

I’m co-author of three papers at The 14th International Conference on Artificial Intelligence and Law (ICAIL 2013), Rome, Italy, The Netherlands.
Il Colloseo, Rome, Italy
Tara Athan, Harold Boley, Guido Governatori, Monica Palmirani, Adrian Paschke, Adam Wyner
In this paper we present the motivation, use cases, design principles, abstract syntax, and initial core of LRML. The LRML core is sufficiently rich for expressing legal sources, time, defeasibility, and deontic operators. An example is provided. LRML is compared to related work.
author = {Tara Athan and Harold Boley and Guido Governatori and Monica Palmirani and Adrian Paschke and Adam Wyner},
title = {{OASIS} {L}egal{R}ule{ML}},
booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law (ICAIL 2013)},
year = {2013},
pages = {3-12},
address = {Rome, Italy}
Argument Schemes for Reasoning with Legal Cases Using Values
Trevor Bench-Capon, Henry Prakken, Adam Wyner, and Katie Atkinson
Argument schemes can provide a means of explicitly describing reasoning methods in a form that lends itself to computation. The reasoning required to distinguish cases in the manner of CATO has been previously captured as a set of argument schemes. Here we present argument schemes that encapsulate another way of reasoning with cases: using preferences between social values revealed in past decisions to decide cases which have no exact matching precedents when the cases are described in terms of factors. We provide a set of schemes, with variations to capture different ways of comparing sets and varying degrees of promotion of values; we formalise these schemes; and we illustrate them with some examples.
author = {Trevor Bench-Capon and Henry Prakken and Adam Wyner and Katie Atkinson},
title = {Argument Schemes for Reasoning about Legal Cases},
booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law (ICAIL 2013)},
year = {2013},
pages = {13-22},
address = {Rome, Italy}
Argumentation Based Tools for Policy-Making
Maya Wardeh, Adam Wyner, Trevor Bench-Capon, and Katie Atkinson
Short paper, so no abstract.
author = {Maya Wardeh and Adam Wyner and Trevor Bench-Capon and Katie Atkinson},
title = {Argumentation Based Tools for Policy-Making},
booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law (ICAIL 2013)},
year = {2013},
pages = {249-250},
address = {Rome, Italy}
Shortlink to this page.
By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Article in Artificial Intelligence and Law Journal for the 25th Anniversary of the International Conference on Artificial Intelligence and Law

A forthcoming special issue of the Journal of Artificial Intelligence and Law will be a long multi-author paper that celebrates 25 years of the International Conference on Artificial Intelligence and the Law.
A History of AI and Law in 50 Papers: 25 years of the International Conference on Artificial Intelligence and the Law
Bench-Capon et al.
Journal of Artificial Intelligence and Law
To appear.
Each of the authors who contributed to the special issue wrote about a paper from the conference from this 25 year period.
For this special issue, I wrote three sections:

The long paper itself serves as an excellent overview of the field these many years.
Shortlink to this page.
By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

TO BE UPDATED: Instructions for Online Collaborative Legal Case Annotation Task

TO BE UPDATED for the SPLeT 2012 task. The information here and in the links here are out of date. The material is being updated for the task, so please return at a later date or email the authors. Thanks for your interest.
— Adam
Wim Peters and I ran a pilot experiment in online, collaborative annotation for legal case factors. The slides are below. Now that we know more about how to present such materials, we need to find a cooperative population of law students to scale up and deepen the work.
Annotating Legal Case Factors with GATE TeamWare
By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

LOAIT Workshop Paper on Legal Text Annotation

A paper I presented at 4th Workshop on Legal Ontologies and Artificial Intelligence Techniques is to appear in the journal Rivista Informatica e diritto, an Italian journal on AI and Law.
Towards Annotating and Extracting Textual Legal Case Elements
Adam Wyner
The paper presents an outline of a method for semantic, conceptual search in legal case documents using the GATE tool.
By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Recent Papers

My colleagues and I have had the papers below accepted for upcoming conferences. The papers are all downloadable from the links provided.
Towards a Structured Online Consultation Tool
Adam Wyner, Katie Atkinson, and Trevor Bench-Capon
ePart August 2011, Deflt, The Netherlands
The Structured Online Consultation tool (SCT) is a component tool in the IMPACT Project which is used to construct and present detailed surveys that solicit feedback from the public concerning issues in public policy. The tool is underwritten by a computational model of argumentation, incorporating fine-grained, interconnected argumentation schemes. While the public responds to easy to understand questions, the answers can be assimilated into a structured framework for analytic purposes, supporting automated reasoning about arguments and counter-arguments.
Multi-agent Based Classifi cation Using Argumentation From Experience
Maya Wardeh, Frans Coenen, Trevor Bench-Capon, and Adam Wyner
PAKDD May 2011, Shenzhen, China
An approach to multi-agent classi fication, using an Argumentation from Experience paradigm is describe, whereby individual agents argue for a given example to be classifi ed with a particular label according to their local data. Arguments are expressed in the form of classi fication rules which are generated dynamically. The advocated argumentation process has been implemented in the PISA multi-agent framework, which is also described. Experiments indicate that the operation of PISA is comparable with other classi fication approaches and that it can be utilised for Ordinal Classifi cation and Imbalanced Class problems.
Note: I was added to this paper to present it at the conference. I’m familiar with the argumentation aspects, but the data-mining is new to me.
Semantic Models for Policy Deliberation
Katie M. Atkinson, Trevor J.M. Bench-Capon, Dan Cartwright and Adam Z. Wyner
ICAIL June 2011, Pittsburgh, USA
Semantic models have received little attention in recent years, much of their role having been taken over by developments in ontologies. Ontologies, however, are static, and so have only a limited role in reasoning about domains in which change matters. In this paper, we focus on the domain of policy deliberation, where policy decisions are designed to change things to realise particular social values. We explore how a particular kind of state transition system can be constructed to serve as a semantic model to support reasoning about alternative policy decisions. The policy making process includes stages that support the construction of a model, which can then be exploited in reasoning. The reasoning itself will be driven by a particular argumentation scheme for practical reasoning, and the ways in which arguments based on this scheme can be attacked and evaluated. The evaluation provides alternative policy positions. The semantics underpin a current web-based implementation, designed to solicit structured feedback on policy proposals.
Towards Formalising Argumentation about Legal Cases
Adam Z. Wyner, Trevor J.M. Bench-Capon, Katie M. Atkinson
ICAIL June 2011, Pittsburgh, USA
In this paper we offer an account of reasoning with legal cases in terms of argumentation schemes. These schemes, and undercutting attacks associated with them, are expressed as defeasible rules of inference that will lend themselves to formalisation within the ASPIC+ framework. We begin by modelling the style of reasoning with cases developed by Aleven and Ashley in the CATO project, which describes cases using factors, and then extend the account to accommodate the dimensions used in Rissland and Ashley’s earlier HYPO project. Some additional scope for argumentation is then identified and formalised.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

Talk at BILETA 2011

I’m giving a talk tomorrow, April 11 2011, at BILETA, the annual conference of the British & Irish Law, Education and Technology Association at Manchester Metropolitan University School of Law. My collaborators are Wim Peters (University of Sheffield) and Fiona Beveridge (University of Liverpool).
The abstract and slides are below:
Web-based Software Tools to Support Students’ Empirical Study of the Law
Adam Wyner (University of Liverpool, Computer Science), Wim Peters (University of Sheffield, Computer Science), and Fiona Beveridge (University of Liverpool, Law School)
The paper investigates and proposes tools to support students in empirically investigating legal cases using text analytic software. Web-based tools can be used to engage and leverage the collective skills and ambitions of law students to crowd-source the development of legal resource materials. Law school students must develop skills in close textual analysis of legal source material such as legal cases. To use source material such as case decisions to reason about how precedents apply in case-based reasoning, law students must learn to identify a range of elements in legal cases, for example, parties, jurisdiction, material facts, legislative and case citations, cause of action, ratio decideni, and others. Moreover, students should be able to address complex queries to a case or a case base (a corpus of cases) in order to answer questions of particular legal interest; for example, about relationships between a judge, parties, cause of action, and ratio. Currently students either simply rely on their own analytic abilities to read a case or find answers to questions; legal search tools (e.g. Lexis-Nexis) provide search support, but are restricted to a limited number of coarse-grained parameters and cannot search for deep, particular semantic relationships in the text. To enable automated support of queries of the corpus, and so enable deep empirical research on cases, it is essential to have a corpus of legal cases which are annotated with machine readable (XML) tags that signal the semantic properties of passages of text. To create such a corpus requires a tool to annotate the text. Such a tool would reinforce students’ examination of the source document. The paper describes recent developments of tools using Semantic Web technologies, text analysis, and web-based annotation support. With the text analysis software, General Architecture for Text Engineering (GATE), which is customised for legal applications, law students can annotate legal cases for a fine-grained range of legally relevant concepts and linguistic relations; they can also use GATE to write grammars and automatically annotate the text. Using GATE TeamWare, an online text annotation tool that automatically evaluates interannotator agreement, students can collaboratively analyse and agree on a gold standard corpus of legal cases. The corpus can be automatically indexed using Lucene, thereby allowing fast results to complex queries over any string or annotation used.
The slides of the talk are here

Workshop on Argumentation and Case-based Reasoning at ICCBR Sept 12-15, 2011

Call for Papers

Argumentation and Case-based Reasoning (ACBR 2011)

September 12, 2011
A workshop at
ICCBR 2011: The International Conference on Case-based Reasoning, September 12-15, 2011
Greenwich, London, United Kingdom
Case-based reasoning is standardly formalised as having four-steps – retrieve, reuse, revise, and retain. In this formalisation, there is little scope for debate. However, in domains such as law, medicine, and product selection, participants (lawyers, doctors, or consumers) may argue for or against a given legal determination, clinical treatment plan, or product choice based on what is retrieved from the case base, how the cases are reused, and what revisions are made to a case. The participants must not only justify their argument, but also defend it against counter-arguments; as well, subsidiary arguments must be justified and defended. Moreover, the information in the case base may be incomplete; different individuals to the dispute may hold alternative views, values, or consumer-oriented goals; and the reasoning itself may only be plausible rather than certain. Given this, we resort to defeasible argumentation on information derived from the case base, where claims only presumptively follow from premises and reasoning about the overall ‘network’ of arguments can be related to alternative contexts or audiences. At the end of the reasoning process, some decision must be made, which may vary depending on audiences.
Recent research on formalising or supporting decision-making in social systems (law, medicine, consumer discussion websites) shows the crucial role of argumentation in structuring, clarifying, and reasoning with respect to complex, possibly inconsistent information. Bringing researchers together to discuss results across domains will lead to greater understanding of commonalities or problems and forward state-of-the-art research on the intersection of and interaction between case-based reasoning and argumentation.
Intended Audence
Researchers working on Argumentation and CBR in any theoretical approach and application domain (Law, Medicine, Web-based consumer sites, Games, etc).
Areas of Interest (preliminary):

  • Relationships between case-bases and argumentation such as argumentation schemes that are designed for particular domains.
  • The content and structure of the case-base as required by participants to the argument.
  • Examples examples and applications of case-based argumentative reasoning.
  • Author Guidelines:
    The workshop solicits full papers and position papers. As well as fully-developed, thoroughly evaluated research, authors are welcome to submit tentative, incremental, and exploratory studies. Papers not accepted as full papers may be accepted as short research abstracts. Submissions will be evaluated by the program committee. Papers should be submitted in LNCS format, with a maximum of 10 pages. Camera-ready copies of papers have to be ready on the 25 of July 2011 (hard deadline) so that they can be included in the workshop proceedings.
    Submissions should be submitted electronically in PDF to the EasyChair site by the deadline (see important dates below). As it stands now, you submit the paper via ICCBR submission page on EasyChair, submitting the paper to Workshop 6: Argumentation and Case-based Reasoning.
    Papers will appear in the proceedings of the conference workshops. Further details about publication are to follow.
    Argumentation and Case-based Reasoning
    Important Dates:
    Paper submission deadline: 27 June 2011 by 00:00 GMT
    Acceptance notification sent: 06 July 2011
    Final camera-ready version deadline: 5 August 2011
    Workshop date: 12 September 2011
    Contact Information:
    Primary contact: Adam Wyner,
    Program Committee Co-Chairs:
    Adam Wyner (University of Liverpool, UK)
    Trevor Bench-Capon (University of Liverpool, UK)
    Program Committee (preliminary):
    Kevin Ashley, University of Pittsburgh
    Katie Atkinson, University of Liverpool
    Frans Coenen, University of Liverpool
    Mehmet Goker, PriceWaterhouseCoopers
    Nancy Green, University of North Carolina
    Stella Heras, Universidad Politecnica de Valencia
    Cindy Marling, Ohio University
    David McSherry, University of Ulster
    Edwina Rissland, University of Massachusetts
    Maya Wardeh, University of Liverpool