- L. Karl Branting, Data-centric and
logic-based models for automated legal problem solving,
AI & Law Journal, Springer
(2017). HTML
Abstract: Logic-based
approaches to legal problem solving model the
rule-governed nature of legal argumentation,
justification, and other legal discourse but suffer from
two key obstacles: the absence of efficient, scalable
techniques for creating authoritative representations of
legal texts as logical expressions; and the difficulty of
evaluating legal terms and concepts in terms of the
language of ordinary discourse. Data-centric techniques
can be used to finesse the challenges offormalizing legal
rules and matching legal predicates with the language of
ordinary parlance by exploiting knowledge latent in
legal corpora. However, these techniques typically are
opaque and unable to support the rule-governed discourse
needed for persuasive argumentation and
justification. This paper distinguishes representative
legal tasks to which each approach appears to be
particularly well suited and proposes a hybrid model
that exploits the complementarity of each.
- L. Karl Branting, Context-Sensitive Detection of Local Community
Structure, Social Network Analysis and Mining, 1869-5450:1-11, Springer
(2011). Mitre Portal
Abstract: Local methods for detecting community structure are necessary when a graph's
size or node-expansion cost make global community-detection methods infeasible.
Various algorithms for local community detection have been proposed, but there
has been little analysis of the circumstances under which one approach is
preferable to another. This paper describes an evaluation comparing the accuracy
of five alternative local community-detection algorithms in detecting two
distinct types of community structures—vertex partitions that maximize
modularity, and link clusters that maximize partition density—in a variety of
graphs. In this evaluation, the algorithm that most accurately identified
modularity-maximizing community structure in a given graph depended on how
closely the graph's degree distribution approximated a power-law distribution.
When the target community structure was partition-density maximization, however,
an algorithm based on spreading activation generally performed best, regardless
of degree distribution.
- L.
Karl Branting, Information Theoretic Criteria for Community Detection,
Lecture Notes in Computer Science LNCS 5498, Proceedings of SNA-KDD
2008, to appear 2010. PDF (237K, 17 pages)
Abstract:
Many
algorithms for finding community structure in graphs search for a
partition that maximizes modularity. However, recent work has
identified two important limitations of modularity as a community
quality criterion: a resolution limit; and a bias towards finding
equal-sized communities. Information-theoretic approaches that search
for partitions that minimize description length are a recent
alternative to modularity. This paper shows that two
information-theoretic algorithms are them- selves subject to a
resolution limit, identifies the component of each approach that is
responsible for the resolution limit, proposes a variant, SGE (Sparse
Graph Encoding), that addresses this limitation, and demonstrates on
three artificial data sets that (1) SGE does not exhibit a resolution
limit on sparse graphs in which other approaches do, and that (2)
modularity and the compression-based algorithms, including SGE, behave
similarly on graphs not subject to the resolution limit.
- L.
Karl Branting, A Reduction-Graph
Model of Precedent in Legal Analysis, Artificial Intelligence,
150(1-2):59-95, (November 2003). ACM Portal
Abstract: Legal analysis is
a task underlying many forms of legal problem solving. In the
Anglo-American legal system, legal analysis is based in part on legal
precedents, previously decided cases. This paper describes a
reduction-graph model of legal precedents that accounts for a key
characteristic of legal precedents: a precedent's relevance to
subsequent cases is determined by the theory under which the precedent
is decided. This paper identifies the implementation requirements for
legal analysis using the reduction-graph model of legal precedents and
describes GREBE, a program that satisfies these requirements.
- L. Karl Branting, Learning Feature Weights from
Customer Return-Set Selections, The Journal of Knowledge and
Information Systems (KAIS) 6(2) March (2004). PDF (1,199K, 16 pages)
Abstract: This paper
describes LCW, a procedure for learning customer preferences
represented as feature weights by observing customers' selections from
return sets. An empirical evaluation on simulated customer behavior
indicated that uninformed hypotheses about customer weights lead to low
ranking accuracy unless customers place some importance on almost all
features or the total number of features is quite small. In contrast,
LCW's estimate of the mean preferences of a customer population
improved as the number of customers increased, even for larger numbers
of features of widely differing importance. This improvement in the
estimate of mean customer preferences led to improved prediction of
individual customer's rankings, irrespective of the extent of variation
among customers and whether a single or multiple retrievals were
permitted. The experimental results suggest that the return set that
optimizes benefit may be smaller for customer populations with little
variation than for customer populations with wide variation.
- L. Karl Branting, Name-Matching Algorithms for Legal
Case-Management Systems, The Journal of Information, Law and Technology
(JILT) 2002(1). JILT 2002 Portal
Abstract: Name matching -
recognizing when two different strings are likely to denote the same
entity, is essential for automatic detection of conflicts of interest
in legal case-management systems (LCMSs). Unfortunately, most
name-matching algorithms developed for LCMSs are proprietary and are
therefore not amenable to independent evaluation, improvement, or
comparison. This paper proposes a three-step framework for name
matching in LCMSs, identifies how each step in the framework addresses
the naming variations that typically arise in LCMSs, describes several
alternative approaches to each step, and evaluates the performance of
various combinations of the alternatives on a representative collection
of names drawn from a United States District Court LCMS. The best
tradeoff between accuracy and efficiency in this LCMS was achieved by
algorithms that standardize capitalization, spacing, and punctuation;
filter redundant terms; index using an abstraction function that is
both order-insensitive and tolerant of small numbers of omissions or
additions; and compare names in a symmetrical, word-by-word fashion.
- L. Karl Branting, An Advisory System for Pro Se
Protection Order Applicants, International Review of Law, Computers
& Technology 14(3), (2000). PDF (5,180K, 21 pages)
Abstract: Pro se litigants
constitute a growing burden to the judiciary. Advisory systems designed
to help litigants understand the available legal remedies and satisfy
the substantive and procedural requirements to obtain those remedies
have the potential to reduce this burden. This paper presents a
four-component model of advisory systems for pro se litigants. This
model was implemented in the Protection Order Advisory (POA), an
advisory system for pro se Protection Order applicants. POA illustrates
how existing inference, document-drafting, and interface-design
techniques can be used to construct advisory systems for pro se
litigants in a wide range of legal domains for which (1) determining
whether a prima facie case is satisfied does not require open-textured
reasoning, and (2) the documents required to initiate an action are
characterized by homogeneity and simple structure.
-
L. Karl Branting, Techniques for Automated Judicial
Document Drafting, International Journal of Law & Information
Technology, 6(2):214-229 (1998). PDF (743K, 11 pages)
Abstract: Document drafting
is an essential component of judicial problem solving. This paper
distinguishes several classes of judicial documents based on (1) the
stage of the judicial process in which they are created, (2) the
complexity of the documents, and (3) the party who drafts the
documents: a judge, judicial support personnel, or a litigant. Three
approaches to automated document drafting are identified and the
applicability of the these approaches to each class of judicial
document is described. The paper concludes with a description of
several implemented prototype systems for drafting judicial documents
at various stages of the judicial process.
- L. Karl Branting, James C. Lester, and Charles B.
Callaway, Automating Judicial Document Drafting: A Discourse-Based
Approach, Artificial Intelligence and Law, 6(2-4):105-110 (1998). PDF 634K, 49 pages)
Abstract: Document drafting
is a central judicial problem-solving activity. Development of
automated systems to assist judicial document drafting has been impeded
by the absence of an explicit model of (1) the connection between the
document drafter's goals and the text intended to achieve those goals,
and (2) the rhetorical constraints expressing the stylistic and
discourse conventions of the document's genre. This paper proposes a
model in which the drafter's goals and the stylistic and discourse
conventions are represented in a discourse structure consisting of a
tree of illocutionary and rhetorical operators with document text as
leaves. A document grammar based on the discourse structures of a
representative set of documents can be used to synthesize a wide range
of additional documents from sets of case facts. The applicability of
this model to a representative class of judicial
orders--jurisdictional show-cause orders--is demonstrated by
illustrating (1) the analysis of show-cause orders in terms of
discourse structures, (2) the derivation of a ocument grammar from
discourse structures of two typical show-cause orders, and (3) the
synthesis of a new show-cause order from the document grammar.
- L. Karl Branting, John D. Hastings, and Jeffrey A.
Lockwood, Integrating Cases and Models for Prediction in Biological
Systems, AI Applications 11(1):29-48 (1997). PDF (255K, 31 pages)
Abstract: Many complex
biological systems are characterized both by incomplete models and
limited empirical data. Accurate prediction of the behavior of such
systems requires exploitation of multiple, individually incomplete,
knowledge sources. Model-based adaptation is a technique for
integrating case-based reasoning with model-based reasoning to predict
the behavior of biological systems. This approach is implemented in
CARMA, a system for rangeland grasshopper management advising that
implements a process model derived from protocol analysis of human
expert problem-solving episodes. CARMA's ability to predict the forage
consumption judgments of expert pest managers was empirically compared
to that of case-based and model-based reasoning techniques in
isolation. This evaluation provided initial confirmation for the
hypothesis that an integration of model-based and case-based reasoning
can lead to more accurate predictions than either technique
individually.
- L. Karl Branting and Pat Broos, Automated
Acquisition of User Preferences. International Journal of
Human-Computer Studies, 46:55-77 (1997). PDF (436K, 43 pages)
Abstract: Decision support
systems often require knowledge of users' preferences. However,
preferences may vary among individual users or be difficult for users
to articulate. This paper describes how user preferences can be
acquired in the form of preference predicates by a learning apprentice
system and proposes two new instance-based algorithms for preference
predicate acquisition: 1ARC and Compositional Instance-Based Learning
(CIBL). An empirical evaluation using simulated preference behavior
indicated that the instance-based approaches are preferable to
decision-tree induction and perceptrons as the learning component of a
learning apprentice system if representation of the relevant
characteristics of problem-solving states requires a large number of
attributes, if attributes interact in a complex fashion, or if there
are very few training instances. Conversely, decision-tree induction or
perceptron learning is preferable if there are a small number of
attributes and the attributes do not interact in a complex fashion
unless there are very few training instances. When tested as the
learning component of a learning apprentice system used by astronomers
for scheduling astronomical observations, both CIBL and decision-tree
induction rapidly achieved useful levels of accuracy in predicting the
astronomers' preferences.
- John Hastings, Karl Branting, and Jeff Lockwood, A
Multi-Paradigm Reasoning System for Rangeland Management. Computers and
Electronics in Agriculture, 16(1):47-67 (1996). PDF 896K, 23 pages)
Abstract: Polycultural
agroecosystems, such as rangelands, are too complex and poorly
understood to permit precise numerical simulation. Management decisions
that depend on predictions of the behavior of such systems therefore
require a variety of knowledge sources and reasoning techniques. Our
approach to designing a computer system to provide advice concerning
such systems is to incorporate a variety of reasoning paradigms,
permitting the computer system to apply whatever reasoning paradigm is
most appropriate to each task as it arises in the process of giving
advice. This approach is based on a process description of expert human
problem solving that uses four different reasoning paradigms:
model-based reasoning; case-based reasoning; rule-based reasoning; and
probabilistic reasoning. The process description is implemented in
CARMA, a computer system for advising ranchers about the best response
to rangeland grasshopper infestations. CARMA reflects an approach that
attempts to emulate the human ability to integrate multiple knowledge
sources and reasoning techniques in a flexible and opportunistic
fashion. The goal of this approach is to enable computer systems to
optimize the use of the diverse and incomplete knowledge sources and to
produce patterns of reasoning that resemble those of human decision
makers.
- L. Karl Branting, A Computational Model of Ratio
Decidendi. Artificial Intelligence and Law, 2(1):1-31 (1994). PDF (476K, 54 pages)
Abstract: This paper
proposes a model of ratio decidendi as a justification structure
consisting of a series of reasoning steps, some of which relate
abstract predicates to other abstract predicates and some of which
relate abstract predicates to specific facts. This model satisfies an
important set of characteristics of ratio decidendi identified from the
jurisprudential literature. In particular, the model shows how the
theory under which a case is decided controls its precedential effect.
By contrast, a purely exemplar-based model of ratio decidendi fails to
account for the dependency of precedential effect on the theory of
decision.
|