Kevin D. Ashley

AILAW Journal 2021 Journal Article

Legal information retrieval for understanding statutory terms

• Jaromír Šavelka
• Kevin D. Ashley

Abstract In this work we study, design, and evaluate computational methods to support interpretation of statutory terms. We propose a novel task of discovering sentences for argumentation about the meaning of statutory terms. The task models the analysis of past treatment of statutory terms, an exercise lawyers routinely perform using a combination of manual and computational approaches. We treat the discovery of sentences as a special case of ad hoc document retrieval. The specifics include retrieval of short texts (sentences), specialized document types (legal case texts), and, above all, the unique definition of document relevance provided in detailed annotation guidelines. To support our experiments we assembled a data set comprising 42 queries (26, 959 sentences) which we plan to release to the public in the near future in order to support further research. Most importantly, we investigate the feasibility of developing a system that responds to a query with a list of sentences that mention the term in a way that is useful for understanding and elaborating its meaning. This is accomplished by a systematic assessment of different features that model the sentences’ usefulness for interpretation. We combine features into a compound measure that accounts for multiple aspects. The definition of the task, the assembly of the data set, and the detailed task analysis provide a solid foundation for employing a learning-to-rank approach.

AILAW Journal 2010 Journal Article

Emerging AI & Law approaches to automating analysis and retrieval of electronically stored information in discovery proceedings

• Kevin D. Ashley
• Will Bridewell

Abstract This article provides an overview of, and thematic justification for, the special issue of the journal of Artificial Intelligence and Law entitled “E-Discovery”. In attempting to define a characteristic “AI & Law” approach to e-discovery, and since a central theme of AI & Law involves computationally modeling legal knowledge, reasoning and decision making, we focus on the theme of representing and reasoning with litigators’ theories or hypotheses about document relevance through a variety of techniques including machine learning. We also identify two emerging techniques for enabling users’ document queries to better express the theories of relevance and connect them to documents: social network analysis and a hypothesis ontology.

AILAW Journal 2009 Journal Article

Automatically classifying case texts and predicting outcomes

• Kevin D. Ashley
• Stefanie Brüninghaus

Abstract Work on a computer program called SMILE + IBP (SMart Index Learner Plus Issue-Based Prediction) bridges case-based reasoning and extracting information from texts. The program addresses a technologically challenging task that is also very relevant from a legal viewpoint: to extract information from textual descriptions of the facts of decided cases and apply that information to predict the outcomes of new cases. The program attempts to automatically classify textual descriptions of the facts of legal problems in terms of Factors, a set of classification concepts that capture stereotypical fact patterns that effect the strength of a legal claim, here trade secret misappropriation. Using these classifications, the program can evaluate and explain predictions about a problem’s outcome given a database of previously classified cases. This paper provides an extended example illustrating both functions, prediction by IBP and text classification by SMILE, and reports empirical evaluations of each. While IBP’s results are quite strong, and SMILE’s much weaker, SMILE + IBP still has some success predicting and explaining the outcomes of case scenarios input as texts. It marks the first time to our knowledge that a program can reason automatically about legal case texts.

AILAW Journal 2009 Journal Article

Teaching a process model of legal argument with hypotheticals

• Kevin D. Ashley

Abstract The research described here explores the idea of using Supreme Court oral arguments as pedagogical examples in first year classes to help students learn the role of hypothetical reasoning in law. The article presents examples of patterns of reasoning with hypotheticals in appellate legal argument and in the legal classroom and a process model of hypothetical reasoning that relates them to work in cognitive science and Artificial Intelligence. The process model describes the relationships between an advocate’s proposed test for deciding a case or issue, the facts of the hypothetical and of the case to be decided, and the often conflicting legal principles and policies underlying the issue. The process model of hypothetical reasoning has been partially implemented in a computerized teaching environment, LARGO (“Legal ARgument Graph Observer”) that helps students identify, analyze, and reflect on episodes of hypothetical reasoning in oral argument transcripts. Using LARGO, students reconstruct examples of hypothetical reasoning in the oral arguments by representing them in simple diagrams that focus students on the proposed test, the hypothetical challenge to the test, and the responses to the challenge. The program analyzes the diagrams and provides feedback to help students complete the diagrams and reflect on the significance of the hypothetical reasoning in the argument. The article reports the results of experiments evaluating instruction of first year law students at the University of Pittsburgh using the LARGO program as applied to Supreme Court personal jurisdiction cases. The learning results so far have been mixed. Instruction with LARGO has been shown to help law student volunteers with lower LSAT scores learn skills and knowledge regarding hypothetical reasoning better than a text-based approach, but not when the students were required to participate. On the other hand, the diagrams students produce with LARGO have been shown to have some diagnostic value, distinguishing among law students on the basis of LSAT scores, posttest performance, and years in law school. This lends support to the underlying model of hypothetical argument and suggests using LARGO as a pedagogically diagnostic tool.

KER Journal 2005 Journal Article

Case-based reasoning and law

• Edwina L. Rissland
• Kevin D. Ashley
• L. Karl Branting

A primary research stream that contributed to the birth of case-based reasoning (CBR) was Artificial Intelligence and Law. Since law is largely about cases, it is a particularly interesting domain for CBR researchers. This article surveys some of the historically significant systems and developments in this field.

KER Journal 2005 Journal Article

Textual case-based reasoning

• Rosina O. Weber
• Kevin D. Ashley
• Stefanie Brüninghaus

This commentary provides a definition of textual case-based reasoning (TCBR) and surveys research contributions according to four research questions. We also describe how TCBR can be distinguished from text mining and information retrieval. We conclude with potential directions for TCBR research.

AIJ Journal 2003 Journal Article

AI and Law: A fruitful synergy

• Edwina L. Rissland
• Kevin D. Ashley
• R.P. Loui

AIJ Journal 2003 Journal Article

Law, learning and representation

• Kevin D. Ashley
• Edwina L. Rissland

In machine learning terms, reasoning in legal cases can be compared to a lazy learning approach in which courts defer deciding how to generalize beyond the prior cases until the facts of a new case are observed. The HYPO family of systems implements a “lazy” approach since they defer making arguments how to decide a problem until the programs have positioned a new problem with respect to similar past cases. In a kind of “reflective adjustment”, they fit the new problem into a patchwork of past case decisions, comparing cases in order to reason about the legal significance of the relevant similarities and differences. Empirical evidence from diverse experiments shows that for purposes of teaching legal argumentation and performing legal information retrieval, HYPO-style systems' lazy learning approach and implementation of aspects of reflective adjustment can be very effective.

AILAW Journal 2002 Journal Article

A note on dimensions and factors

• Edwina L. Rissland
• Kevin D. Ashley

In this short note, we discuss several aspectsof “dimensions” and the related constructof “factors”. We concentrate on those aspectsthat are relevant to articles in this specialissue, especially those dealing with the analysisof the wild animal cases discussed inBerman and Hafner's 1993 ICAIL article. We reviewthe basic ideas about dimensions,as used in HYPO, and point out differences withfactors, as used in subsequent systemslike CATO. Our goal is to correct certainmisconceptions that have arisen over the years.

AILAW Journal 2002 Journal Article

An AI model of case-based legal argument from a jurisprudential viewpoint

• Kevin D. Ashley

This article describes recent jurisprudential accountsof analogical legal reasoning andcompares them in detail to the computational modelof case-based legal argument inCATO. The jurisprudential models provide a theoryof relevance based on low-levellegal principles generated in a process ofcase-comparing reflective adjustment. Thejurisprudential critique focuses on the problemsof assigning weights to competingprinciples and dealing with erroneously decidedprecedents. CATO, a computerizedinstructional environment, employs ArtificialIntelligence techniques to teach lawstudents how to make basic legal argumentswith cases. The computational modelhelps students test legal hypotheses againsta database of legal cases, draws analogiesto problem scenarios from the database, andcomposes arguments by analogy with a setof argument moves. The CATO model accountsfor a number of the important featuresof the jurisprudential accounts, includingimplementing a kind of reflective adjustment.It also avoids some of the problems identifiedin the critique; for instance, it deals withweights in a non-numeric, context-sensitivemanner. The article concludes by describingthe contributions AI research can make tojurisprudential investigations of complexcognitive phenomena of legal reasoning. Forinstance, unlike the jurisprudential models,CATO provides a detailed account of how togenerate multiple interpretations of a citedcase, downplaying or emphasizing the legalsignificance of distinctions in terms of thepurposes of the law as the argument contextdemands.

IJCAI Conference 1997 Conference Paper

Reasoning Symbolically About Partially Matched Cases

• Kevin D. Ashley
• Vincent Aleven

In teaching case-based argumentation skills, the CATO program, an intelligent learning environment, guides students' assessments of partial matches between problems and cases by generating alternative interpretations of the similarities and differences. CATO's Factor Hierarchy captures information about the significance of similarities and differences given the normative purposes of the domain classification. Its algorithms for emphasizing or downplaying significance tailor interpretations to the comparison context, block interpretations strongly contradicted by other factors and strategically determine how and how abstractly to characterize a difference. An empirical evaluation confirmed CATO's effectiveness in teaching basic argumentation skills.

AILAW Journal 1992 Journal Article

Case-based reasoning and its implications for legal expert systems

• Kevin D. Ashley

Abstract Reasoners compare problems to prior cases to draw conclusions about a problem and guide decision making. All Case-Based Reasoning (CBR) employs some methods for generalizing from cases to support indexing and relevance assessment and evidences two basic inference methods: constraining search by tracing a solution from a past case or evaluating a case by comparing it to past cases. Across domains and tasks, however, humans reason with cases in subtly different ways evidencing different mixes of and mechanisms for these components. In recent CBR research in Artificial Intelligence (AI), five paradigmatic approaches have emerged: statistically-oriented, model-based, planning/design-oriented, exemplar-based, and adversarial or precedent-based. The paradigms differ in the assumptions they make about domain models, the extent to which they support symbolic case comparison, and the kinds of inferences for which they employ cases. Reasoning with cases is important in legal practice of all kinds, and legal practice involves a wide variety of case-based tasks and methods. The paradigms' respective benefits and costs suggest different approaches for different legal tasks. CBR research and development in the field of AI and Law should be pursued vigoriously for several reasons. CBR can supplement rule-based expert systems, improving their abilities to reason about statutory predicates, solve problems efficiently, and explain their results. CBR can also contribute to the design of intelligent legal data retrieval systems and improve legal document assembly programs. Finally, in cognitive studies of various fields, it can model methods of transforming ill-structured problems into better structured ones through the use of case comparisons.

AAAI Conference 1992 Conference Paper

Generating Dialectical Examples Automatically

• Kevin D. Ashley

We identify and illustrate five important kinds of Dialectical Examples, standard configurations of cases which enable an arguer to justify rhetorical assertions effectively by example. Our computer program generates Argument Contexts, collections of cases that instantiate Dialectical Examples from an on-line database of cases according to a user’ s general specifications. The Argument Context generation program provides a human or automated tutor a stock of Dialectical Examples to teach novice advocates (first year law students) how to recognize, carry out and respond to the associated rhetorical moves. Although generating such examples is very hard for humans even when dealing with small numbers of cases, our program generates and organizes such examples quickly and effectively. In a preliminary experiment, we employed program-generated Argument Contexts manually to teach basic argument skills to first year law students with good results. Our ability to define such complex examples declaratively in terms of logical expressions of Loom concepts and relations affords a number of advantages over previous work. Topic: argument from experience, law, education

IJCAI Conference 1989 Conference Paper

Defining Salience in Case-Based Arguments

• Kevin D. Ashley

AAAI Conference 1988 Conference Paper

Waiting on Weighting: A Symbolic Least Commitment Approach

• Kevin D. Ashley

AAAI Conference 1987 Conference Paper

Compare and Contrast: A Test of Expertise

• Kevin D. Ashley

In this paper we present three key elements of case-based reasoning ("CBR") and describe how these are realized in our HYPO program which performs legal reasoning in the domain of trade secret law by comparing and contrasting cases. More specifically, the key elements involve how prior cases are used for: (1) Credit assignment of factual features; (2) Justification; and (3) Argument in domains that do not necessarily have strong causal theories or well-understood empirical regularities. We show how HYPO uses "dimensions", "case-analysis-record" and "claim lattice" mechanisms to perform indexing and relevancy assessment of past cases dynamically and how it compares and contrasts cases to come up with the best cases pro and con a decision.