Abstract. In the last ten years there has been a significant amount of research in Machine Translation within a “new ” paradigm of empirical approaches, often labelled collectively as “Example-based” approaches. The first manifestation of this approach caused some surprise and hostility among observers more used to different ways of working, but the techniques were quickly adopted and adapted by many researchers, often creating hybrid systems. This paper reviews the various research efforts within this paradigm reported to date, and attempts a categorisation of different manifestations of the general approach.

ion in Case-Based Reasoning Ralph Bergmann and Wolfgang Wilke University of Kaiserslautern, Centre for Learning Systems and Applications (LSA) Dept. of Computer Science, P.O.-Box 3049, D-67653 Kaiserslautern, Germany E-Mail: fbergmann,wilkeg@informatik.uni-kl.de Abstract. This paper addresses the role of abstraction in case-based reasoning. We develop a general framework for reusing cases at several levels of abstraction, which is particularly suited for describing and analyzing existing and designing new approaches of this kind. We argue that in synthetic tasks (e.g. configuration, design, and planning), abstraction can be successfully used to improve the efficiency of similarity assessment, retrieval, and adaptation. Furthermore, a case-based planning system, called Paris, is described and analyzed in detail using this framework. An empirical study done with Paris demonstrates significant advantages concerning retrieval and adaptation efficiency as well as flexibility of adaptation....

When problems are solved through reasoning from cases, the primary kind of knowledge is contained in the specific cases which are stored in the case base. However, in many situations additional background-knowledge is required to cope with the requirements of an application. We describe an approach to integrate such general knowledge into the reasoning process in a way that it complements the knowledge contained in the cases. This general knowledge itself is not sufficient to perform any kind of model-based problem solving, but it is required to interpret the available cases appropriately. Background knowledge is expressed by two different kinds of rules that both must be formalized by the knowledge engineer: Completion rules describe how to infer additional features out of known features of an old case or the current query case. Adaptation rules describe how an old case can be adapted to fit the current query. This paper shows how these kinds of rules can be integrated into an object-...

This paper presents a criterion of comparison between two case bases for a case-based system for which the retrieval process is done thanks to a similarity metric. Such a criterion can be useful for at least two things. First, it allows to dene what a better case base of a given size can be. Second it enables us to build a "forgetting criterion" which aims at answering the question "What are the p cases that can be lost from the base that conduct to a minimal loss of performance?" The definition of case-based reasoning given in this paper stresses the fact that the goal of the similarity measure is to give an a priori estimation of the performance of the adaptation process. With an introducing example the "locksmith's problem" and then more generally, the criterion is defined thanks to a number associated with each case base; this number is characteristic of the mean performance of the system working with this base. It seems that very few results can be demonstrated without ...

This paper looks at EBMT from the perspective of the Case-based Reasoning (CBR) paradigm. We attempt to describe the task of machine translation (MT) seen as a potential application of CBR, and attempt to describe MT in standard CBR terms. The aim is to see if other applications of CBR can suggest better ways to approach EBMT.

ion Hierarchies L. Karl Branting Department of Computer Science University of Wyoming P.O. Box 3682 Laramie, WY 82071 karl@index.uwyo.edu (307) 766-4258 / FAX: -4036 Abstract. Stratified case-based reasoning (Scbr) is a technique in which case abstractions are used to assist case retrieval, matching, and adaptation. Previous work showed that Scbr can significantly decrease the computational expense required for retrieval, matching, and adaptation in a route-finding domain characterized by abstraction hierarchies with the downward refinement property. This work explores the effectiveness of Scbr in hierarchies without the downward refinement property. In an experimental evaluation using such hierarchies (1) Scbr significantly decreased search cost in hierarchies without the downward refinement property, although the speedup over ground-level A was not as great as in refinable hierarchies, (2) little difference was observed in Scbr search costs between case libraries created top-down...

When Konrad Lorenz was awarded the Nobel Prize for medicine in 1973 he delivered the lecture "Analogy as a Source of Knowledge" and acknowledged that "...this procedure (analogical

. Two major problems in case-based reasoning are the efficient and justified retrieval of source cases and the adaptation of retrieved solutions to the conditions of the target. For analogical theorem proving by induction, we describe how a solution-relevant abstraction can restrict the retrieval of source cases and the mapping from the source problem to the target problem and how it can determine reformulations that further adapt the source solution. 1 Introduction Case-based reasoning retrieves one or more source problems and their solutions in order to transfer and adapt the source solution to the needs of a given target problem. The efficient retrieval of similar source problems from a large case-base has been a major issue in the case-based reasoning research which has employed efficient inductive techniques for learning indices, with similarity measures, with the retrieval from a case-base of abstracted problems, and with analytically extracting relevant features of problems for...

We present a similarity criterion based on feature weighting. Feature weights are recomputed dynamically according to the performance of cases during problem solving episodes. We will also present a novel algorithm to analyze and explain the performance of the retrieved cases and to determine the features whose weights need to be recomputed. We will perform experiments and show that the integration in a feature weighting model of our similarity criterion with our analysis algorithm improves the adaptability of the retrieved cases by converging to best weights for the features over a period of multiple problem solving episodes. 1 Introduction An essential factor influencing the effectiveness of case-based problem solving is the retrieval phase (Aamodt and Plaza, 1994). In the context of planning and design, retrieval means searching for adaptable cases (Smyth and Keane, 1994; Marir and Watson, 1995; Smyth and Keane, 1995). Thus, any similarity criterion should measure the adaptation ef...

ION 9 The left side of figure 5 outlines a plan for manufacturing the workpiece shown in figure 4, under the supposition that there is a left and a right cutting-tools available. Dashed boxes represent plan-steps and the arcs pointing downwards indicate the partial-order for performing them. This plan states that for removing u-cut1, the workpiece must be clamp from Ascend-1 and the left tool must be used. After that, u-cut2 is removed by using the right tool. This plan contains also the information that clamping from Side2 failed because it does not have any perforation (node labeled R). Suppose now that a new problem is given consisting of the same workpiece, but this time there is only a left tool available. For solving this problem the plan obtained with the two tools will be reused, as illustrated in figure 5. The horizontal arrows show the decisions of the case that are replayed in the new situation. Particularly the decisions concerning the manufacturing of u-cut1 can be replay...