Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Modeling Purposive Legal Argumentation and Case Outcome Prediction using Argument Schemes�in the Value Judgment Formalism

Grabmair, Matthias (2016) Modeling Purposive Legal Argumentation and Case Outcome Prediction using Argument Schemes�in the Value Judgment Formalism. Doctoral Dissertation, University of Pittsburgh.

[img]
Preview
PDF
Primary Text

Download (1MB)

Abstract

Artificial Intelligence and Law studies how legal reasoning can be formalized in order to eventually be able to develop systems that assist lawyers in the task of researching, drafting and evaluating arguments in a professional setting. To further this goal, researchers have been developing systems, which, to a limited extent, autonomously engage in legal reasoning, and argumentation on closed domains. This dissertation presents the Value Judgment Formalism and its experimental implementation in the VJAP system, which is capable of arguing about, and predicting outcomes of, a set of trade secret misappropriation cases.

VJAP argues about cases by creating an argument graph for each case using a set of argument schemes. These schemes use a representation of values underlying trade secret law and effects of facts on these values. VJAP argumentatively balances effects in the given case and analogizes it to individual precedents and the value tradeoffs in those precedents. It predicts case outcomes using a confidence measure computed from the argument graph and generates textual legal arguments justifying its predictions. The confidence propagation uses quantitative weights assigned to effects of facts on values. VJAP automatically learns these weights from past cases using an iterative optimization method.

The experimental evaluation shows that VJAP generates case-based legal arguments that make plausible and intelligent-appearing use of precedents to reason about a case in terms of differences and similarities to a precedent and the value tradeoffs that both contain. VJAP’s prediction performance is promising when compared to machine learning algorithms, which do not generate legal arguments. Due to the small case base, however, the assessment of prediction performance was not statistically rigorous. VJAP exhibits argumentation and prediction behavior that, to some extent, resembles phenomena in real case-based legal reasoning, such as realistically appearing citation graphs.

The VJAP system and experiment demonstrate that it is possible to effectively combine symbolic knowledge and inference with quantitative confidence propagation. In AI\&Law, such systems can embrace the structure of legal reasoning and learn quantitative information about the domain from prior cases, as well as apply this information in a structurally realistic way in the context of new cases.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Grabmair, Matthiasmatthias.grabmair@gmail.comMAG134
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairAshley, Kevinashley@pitt.edu
Committee MemberDruzdzel, Marek J.marek@sis.pitt.eduDRUZDZEL
Committee MemberLesgold, Alan
Committee MemberNyberg, Eric
Date: 6 June 2016
Date Type: Publication
Defense Date: 1 April 2016
Approval Date: 6 June 2016
Submission Date: 14 April 2016
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 155
Institution: University of Pittsburgh
Schools and Programs: Dietrich School of Arts and Sciences > Intelligent Systems
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Artificial Intelligence and Law, Argumentation, Argument Schemes, Case-based Reasoning
Date Deposited: 06 Jun 2016 15:27
Last Modified: 15 Nov 2016 14:32
URI: http://d-scholarship.pitt.edu/id/eprint/27608

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item