An Explainable Approach to Deducing Outcomes in European Court of Human Rights Cases Using ADFs

In this paper we present an argumentation-based approach to representing and reasoning about a domain of law that has previously been addressed through a machine learning approach. The domain concerns cases that all fall within the remit of a specific Article within the European Court of Human Rights. We perform a comparison between the approaches, based on two criteria: ability of the model to accurately replicate the decision that was made in the real life legal cases within the particular domain, and the quality of the explanation provided by the models. Our initial results show that the system based on the argumentation approach improves on the machine learning results in terms of accuracy, and can explain its outcomes in terms of the issue on which the case turned, and the factors that were crucial in arriving at the conclusion.

[1]  Trevor J. M. Bench-Capon.  Neural networks and open texture , 1993, ICAIL '93.

[2]  David Weinberger,et al.  Accountability of AI Under the Law: The Role of Explanation , 2017, ArXiv.

[3]  Trevor J. M. Bench-Capon,et al.  Noise induced hearing loss: Building an application using the ANGELIC methodology , 2018, Argument Comput..

[4]  Kevin D. Ashley,et al.  Automatically classifying case texts and predicting outcomes , 2009, Artificial Intelligence and Law.

[5]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[6]  N. Maccormick,et al.  Interpreting precedents : a comparative study , 1998 .

[7]  Henry Prakken,et al.  A tool in modelling disagreement in law: preferring the most specific argument , 1991, ICAIL '91.

[8]  Trevor J. M. Bench-Capon,et al.  Statement Types in Legal Argument , 2016, JURIX.

[9]  K. Branting,et al.  Semi-Supervised Methods for Explainable Legal Prediction , 2019, ICAIL.

[10]  Kevin D. Ashley,et al.  Predicting outcomes of case based legal arguments , 2003, ICAIL.

[11]  Trevor J. M. Bench-Capon,et al.  Realising ANGELIC Designs Using Logiak , 2019, JURIX.

[12]  Kevin D. Ashley,et al.  Using Factors to Predict and Analyze Landlord-Tenant Decisions to Increase Access to Justice , 2019, ICAIL.

[13]  L. Thorne McCarty,et al.  Reflections on "Taxman": An Experiment in Artificial Intelligence and Legal Reasoning , 1977 .

[14]  Trevor J. M. Bench-Capon,et al.  Accommodating change , 2016, Artificial Intelligence and Law.

[15]  Nikolaos Aletras,et al.  Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective , 2016, PeerJ Comput. Sci..

[16]  Masha Medvedeva,et al.  Using machine learning to predict decisions of the European Court of Human Rights , 2019, Artificial Intelligence and Law.

[17]  Trevor J. M. Bench-Capon.  HYPO’S legacy: introduction to the virtual special issue , 2017, Artificial Intelligence and Law.

[18]  Trevor J. M. Bench-Capon,et al.  Reasoning with Legal Cases: Analogy or Rule Application? , 2019, ICAIL.

[19]  Stefan Woltran,et al.  Abstract Dialectical Frameworks , 2010, KR.

[20]  Henry Prakken,et al.  An abstract framework for argumentation with structured arguments , 2010, Argument Comput..

[21]  Dan Hunter.  Looking for Law in All the Wrong Places , 1994 .

[22]  Vincent A. W. M. M. Aleven,et al.  Teaching case-based argumentation through a model and examples , 1997 .

[23]  Henry Prakken.  Modelling Accrual of Arguments in ASPIC+ , 2019, ICAIL.

[24]  Trevor J. M. Bench-Capon,et al.  Relating the ANGELIC Methodology and ASPIC+ , 2018, COMMA.

[25]  Kevin D. Ashley,et al.  A case-based system for trade secrets law , 1987, ICAIL '87.