NoteCards is a general hypermedia environment designed to help people work with ideas. Its intended users are authors, designers, and other intellectual laborers engaged in analyzing information, designing artifacts, and generally processing ideas. The system provides these users with a variety of hypermedia-based tools for collecting, representing, managing, interrelating, and communicating ideas. This paper presents the NoteCards system as a foil against which to explore some of the major limitations of the current generation of hypermedia systems. In doing so, this paper highlights seven of the major issues that must be addressed in the next generation of hypermedia systems. These seven issues are: search and query, composite nodes, virtual structures, computational engines, versioning, collaborative work, and tailorability. For each of these issues, the papers describes the limitations inherent in NoteCards and the prospects for doing improving the situation in future systems.

A long-standing difficulty for connectionist modeling has been how to represent variable-sized recursive data structures, such as trees and lists, in fixed-width patterns. This paper presents a connectionist architecture which automatically develops compact distributed representations for such compositional structures, as well as efficient accessing mechanisms for them. Patterns which stand for the internal nodes of fixed-valence trees are devised through the recursive use of back-propagation on three-layer autoassociative encoder networks. The resulting representations are novel, in that they combine apparently immiscible aspects of features, pointers, and symbol structures. They form a bridge between the data structures necessary for high-level cognitive tasks and the associative, pattern recognition machinery provided by neural networks. 2 J. B. Pollack 1. Introduction One of the major stumbling blocks in the application of Connectionism to higherlevel cognitive tasks, such as Na...

This article outlines an approach that avoids these problems by choosing a retrieval method that utilizes minimal repository structure to effectively support the process of finding software components. The approach is demonstrated through a pair of proof-ofconcept prototypes: PEEL, a tool to semiautomatically identify reusable components, and CodeFinder, a retrieval system that compensates for the lack of explicit knowledge structures through a spreading activation retrieval process. CodeFinder also allows component representations to be modified while users are searching for information. This mechanism adapts to the changing nature of the information in the repository and incrementally improves the repository while people use it. The combination of these techniques holds potential for designing software repositories that minimize up-front costs, effectively support the search process, and evolve with an organization's changing needs.

This dissertation examines the use of adaptive methods to automatically improve the performance of ranked text retrieval systems. The goal of a ranked retrieval system is to manage a large collection of text documents and to order documents for a user based on the estimated relevance of the documents to the user's information need (or query). The ordering enables the user to quickly find documents of interest. Ranked retrieval is a difficult problem because of the ambiguity of natural language, the large size of the collections, and because of the varying needs of users and varying collection characteristics. We propose and empirically validate general adaptive methods which improve the ability of a large class of retrieval systems to rank documents effectively. Our main adaptive method is to numerically optimize free parameters in a retrieval system by minimizing a non-metric criterion function. The criterion measures how well the system is ranking documents relative to a target ordering, defined by a set of training queries which include the users' desired document orderings. Thus, the system learns parameter settings which better enable it to rank relevant documents before irrelevant. The non-metric approach is interesting because it is a general adaptive method, an alternative to supervised methods for training neural networks in domains in which rank order or prioritization is important. A second adaptive method is also examined, which is applicable to a restricted class of retrieval systems but which permits an analytic solution. The adaptive methods are applied to a number of problems in text retrieval to validate their utility and practical efficiency. The applications include: A dimensionality reduction of vector-based document representations to a vector spa...

As automation increasingly takes its place in industry, especially high-risk industry, it is often blamed for causing harm and increasing the chance of human error when failures occur.-! propose_hat the problem is not the presence of automation, but rather its inappropriate design. The problem is that the operations are performed appropriately under normal conditions, but there is inadequate feedback and interaction with the humans who must control the overall conduct of the task. When the situations exceed the capabilities of the automatic equipment, then the inadequate feedback leads to difficulties for the human controllers. The problem, I suggest, is that the automation is at an intermediate level of intelligence, powerfuI enough to take over control that which used to be done by people, but not powerful enough to handle aIl abnormalities. Moreover, its level of intelligence is insufficient to provide the continual, appropriate feedback that occurs naturally among human operators. This is the source of current difficulties. To solve this problem, the

Repositories must be designed to meet the evolving and dynamic needs of software development organizations. Current software repository methods rely heavily on classification, which exacerbates acquisition and evolution problems by requiring costly classification and domain analysis efforts before a repository can be used effectively. This paper outlines an approach in which minimal initial structure is used to effectively find relevant software components while methods are employed to incrementally improve repository structures. The approach is demonstrated through PEEL, a tool to semi-automatically identify reusable components, and CodeFinder, a retrieval system that compensates for the lack of explicit knowledge structures through spreading activation retrieval and allows component representations to be incrementally improved while users are searching for information. The combination of these techniques yields a flexible software repository that minimizes up-front costs and improves...

Software reuse has long been touted as an effective means to develop software products. But reuse technologies for software have not lived up to expectations. Among the barriers are high costs of building software repositories and the need for effective tools to help designers locate re-usable software. While many design-forreuse and software classification efforts have been proposed, these methods are cost-intensive and cannot effectively take advantage of large stores of design artifacts that many development organizations have accumulated. Methods are needed that take advantage of these valuable resources in a cost-effective manner. This paper describes an approach to the design of tools to help software designers build repositories of software components and locate potentially re-usable software in those repositories. The approach is investigated with a retrieval tool, named CodeFinder, which supports the process of retrieving software components when information needs are ill-defi...

Abstract. This paper presents a short survey of fuzzy and neural approaches to Information Retrieval. The goal of such approaches is to de ne exible Information Retrieval Systems able to deal with the inherent vagueness and uncertainty of the retrieval process. In this survey we address if and how some approaches met their goal. 1.

: INFOrmer is an intelligent filtering system, currently being applied to the management of USENET News articles. An individual may have one or more profiles, each representing a long-term interest of that user. The user profile is then used to measure the relevance of incoming articles and filter out irrelevant documents. A user profile may be modified as a result of relevance feedback, so that it adjusts to users' changing interests. This paper discusses the architecture of INFOrmer and covers the profile/document representation and comparison techniques adopted within the system. Key Words: Text filtering, semantic network, spreading activation, relevance feedback. Category: H.3.3 1 Introduction The increasing popularity of the Internet has led to an explosion in the amount of online data available to the user. One of the major sources of information is through the USENET news feed. The high traffic through many of these newsgroups (estimated at roughly 400 megabytes of textual...

The areas of information retrieval(IR) and information filtering(IF) have become very active research domains. The problems created by the large increase of available online information, of which the vast majority is largely unstructured, have accentuated the need for effective mechanisms to separate the relevant information from the irrelevant. This paper reviews the main approaches and systems used in IR and in the newer field of IF. The paper also includes an overview of systems which utilise social or collaborative filtering techniques to deal with the problem of information overload.