A Symbolic and Connectionist Approach to Legal Information Retrieval

A Symbolic and Connectionist Approach to Legal Information Retrieval

A Symbolic and Connectionist Approach to Legal Information Retrieval

A Symbolic and Connectionist Approach to Legal Information Retrieval

Synopsis

Many existing information retrieval (IR) systems are surprisingly ineffective at finding documents relevant to particular topics. Traditional systems are extremely brittle, failing to retrieve relevant documents unless the user's exact search string is found. They support only the most primitive trial-and-error interaction with their users and are also static. Even systems with so-called "relevance feedback" are incapable of learning from experience with users. SCALIR (a Symbolic and Connectionist Approach to Legal Information Retrieval) -- a system for assisting research on copyright law -- has been designed to address these problems. By using a hybrid of symbolic and connectionist artificial intelligence techniques, SCALIR develops a conceptual representation of document relationships without explicit knowledge engineering. SCALIR's direct manipulation interface encourages users to browse through the space of documents. It then uses these browsing patterns to improve its performance by modifying its representation, resulting in a communal repository of expertise for all of its users.

SCALIR's representational scheme also mirrors the hybrid nature of the Anglo-American legal system. While certain legal concepts are precise and rule-like, others -- which legal scholars call "open-textured" -- are subject to interpretation. The meaning of legal text is established through the parallel and distributed precedence-based judicial appeal system. SCALIR represents documents and terms as nodes in a network, capturing the duality of the legal system by using symbolic (semantic network) and connectionist links. The former correspond to a priori knowledge such as the fact that one case overturned another on appeal. The latter correspond to statistical inferences such as the relevance of a term describing a case. SCALIR's text corpus includes all federal cases on copyright law.

The hybrid representation also suggests a way to resolve the apparent incompatibility between the two prominent paradigms in artificial intelligence, the "classical" symbol-manipulation approach and the neurally-inspired connectionist approach. Part of the book focuses on a characterization of the two paradigms and an investigation of when and how -- as in the legal research domain -- they can be effectively combined.

Excerpt

This book was originally written as a doctoral dissertation at the University of California, San Diego, in 1991. When I began the research a few years earlier, the world of artificial intelligence (AI) was sharply divided into those who defended the dominant symbolic approach and those who saw a revolution in the rebirth of connectionist models. During much of the time I worked on scalir, the kinds of symbolic-connectionist hybrids I advocated were viewed by both camps as inherently flawed. Over time, this perception has begun to change. Today, hybrid systems are the focus of workshops, books, and journals. It is especially appropriate that this book be published now, as research on hybrid systems flourishes.

The changes in legal information retrieval (IR) are slower, but they are coming as well. Last year, West Publishing Co. released a new on-line search system based directly on techniques developed in the ir research community. I would like to believe that experiments such as scalir (which West facilitated) played a small part in encouraging the acceptance of new approaches in commercial ir systems.

Overall, however, the messages of the book are still timely. in fact, more people need to access more textual data in more complex ways than ever. the interweaving of ai, ir, and human-computer interaction will be increasingly important in addressing this problem. Ultimately, that's what scalir is about.

Acknowledgments

This research could literally never have been done without the support of West Publishing Co. and Shepard's/McGraw-Hill. At West, I would like to thank Michael Fix, Steve Haynes, Eileen Knabe, John Niemeyer, and, especially, Andy Desmond for their invaluable assistance. At Shepard's, I would like to thank Teresa Browne, Allan Markolf, Mary Ostgren, and especially Myrna Bennett and Ron Berg. Apple Computer, Inc. also . . .

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.