Toward Integrating Computational Models and Legal Texts
February 6, 2014 12:45pm - 2:00pm
CodeX Speaker Series with
Kevin D. Ashley, University of Pittsburgh School of Law, Learning Research and Development Center, and Intelligent Systems Program
This talk will survey some techniques and prospects for enabling computational models of legal reasoning to work directly and automatically with legal texts to perform legal problem-solving tasks. For example, users of commercial legal information retrieval (IR) systems often want to retrieve not merely sentences with highlighted terms, but arguments and argument-related information, that is, argument retrieval (AR). The talk will illustrate how argument-relevant information could be extracted and applied to retrieve arguments from legal decisions. A second example involves techniques for annotating state statutory texts in a particular domain (dealing with public health emergencies), both manually and using machine learning, so that policy analysts can compare states’ regulatory schemes using network analysis. Related AI and Law work on information extraction from cases and statutes will be highlighted.
About the Speaker:
Dr. Kevin Ashley is a faculty member of the Graduate Program in Intelligent Systems at the University of Pittsburgh, a Senior Scientist at the Learning Research and Development Center, a Professor of Law, and Adjunct Professor of Computer Science. He received a B.A. from Princeton University, J.D. from Harvard Law School and Ph.D. in computer science from the University of Massachusetts. He was a visiting scientist at the IBM Thomas J. Watson Research Center, is a Fellow of the American Association for Artificial Intelligence, and serves as a co-Editor-in-Chief of the journal, Artificial Intelligence and the Law. An expert on computer modeling of legal reasoning, his research has focused on building computational models of legal and ethical reasoning with cases and examples. Professor Ashley is the author of Modeling Legal Argument: Reasoning with Cases and Hypotheticals (1990). His goals are to improve legal information retrieval by leveraging computational models of case-based reasoning and argumentation to support interpretation of legal texts and create intelligent tutoring systems for law students. His NSF-funded ArgumentPeer project combines computer-supported argument diagramming and peer review to improve students’ skills of written legal argument.