Abstract not found

In this paper we describe a methodological analysis of EBMT (Example-Based Machine Translation) based on a CBR (Case-Based Reasoning) perspective. This analysis focuses on adaptation. We argue that, just as in CBR, the overall power of an EBMT system is its ability to adapt examples retrieved to suit the new problem translation. Here we describe a technique whereby reusability is a function of the abstract 'adaptability ' information stored in the cases. This information is exploited during both the adaptation and retrieval stages. 1.

In this paper we describe a methodological analysis of EBMT (Example-based Machine Translation) based on a CBR (Case-Based Reasoning) perspective. This analysis focuses on adaptation. We argue that, just as in CBR, the overall power of an EBMT system is its ability to adapt examples retrieved to suit the new problem translation. Here we describe a technique whereby reusability is a function of the abstract "adaptability" information stored in the cases. This information is exploited during both the adaptation and retrieval stages.

Abstract. The Scone knowledge-base system, currently being developed at Carnegie Mellon University, implements search and inference operations using a set of marker-passing algorithms. These were originally designed for a massively parallel hardware architecture but now are implemented completely in software. The algorithms are fast, relatively simple, and they support efficient implementation of the most heavily used KB features. This paper describes these marker-passing algorithms, their strengths and limitations, and how they are used in Scone. 1

. This paper presents a new approach for learning general knowledge in a diagnostic case-based system through the use of a neural network. We take advantage of the self-adapting nature of the neural network to discover the most relevant features and combination of features for each diagnosis considered. The knowledge acquired by the network is interpreted and mapped into symbolic diagnosis descriptors, which are kept and used by the case-based system to guide its reasoning process, to retrieve cases from a case library and to build explanations. The neural network used in the learning process was the Combinatorial Neural Model, a network that has been combined with other symbolic approaches previously. The paper presents the method used to interpret the knowledge learned in the neural network, as well as the guidelines followed by the reasoning process of the CBR system. An initial experiment in clinical psychology is also reported, where the case-based model introduced here was used ...

Measured inputs in control domains are often continuous. A discretization function is needed to map continuous inputs into multiple intervals or ranges of input values, so that they can be used as symbolic inputs to a rule-based system. The discretization parameters used to determine each interval play a critical role in the overall effectiveness of a rule-based system. This paper introduces a Hybrid Intelligent Architecture (HIA) that exploits the complementary features of expert systems and connectionist architectures to revise the initial domain knowledge and enhance its input characterization. HIA has three building blocks: a KnowledgeBased module, a Statistical module and a Connectionist Architecture module. A well defined format is used to describe the initial knowledge acquired from the application domain in a rule-based format and to enable its mapping into a uniform, three layer network. The statistical module updates both the rule-based and the connectionist subsystems by obs...

E xtracting rules from trained artificial neural networks adds more powerful features to their output decisions. The explanation, validation, and cross-referencing are some of these powerful features. This paper introduces a new rule ordering and evaluation algorithm that orders extracted rules based on three performance measures so they can be used by any generic inference engine. Moreover, it introduces an integration algorithm to inspect the network's output as well as that of the derived rule base subsystem and provides a final decision, along with an associated confidence measure. The Wisconsin breast cancer database is used to train three different feedforward artificial neural networks then three different rule extraction techniques, along with the rule ordering and integration mechanism are used to extract rules from these networks. Experimental results show that the overall system provides superior generalization performance as well as data interpretation even where no prior ...

In this paper we outline hybrid approaches to arti cial neural network-based natural language processing. We start by motivating hybrid symbolic/connectionist processing. Then we suggest various types of symbolic/connectionist integration for language processing: connectionist structure architectures, hybrid transfer architectures, hybrid processing architectures. Furthermore, we focus particularly on loosely coupled, tightly coupled, and fully integrated hybrid processing architectures. We give particular examples of these hybrid processing architectures and argue that the hybrid approach to arti cial neural network-based language processing has a lot of potential to overcome the gap between a neural level and a symbolic conceptual level. ii 1 Motivation for hybrid symbolic/connectionist processing In recent years, the eld of hybrid symbolic/connectionist processing has seen a remarkable

Recognizing coherent structure of a text is an essential task in natural language understanding. It is necessary, for example, to resolve anaphora, ellipsis, and ambiguity. One of the dominant factors of coherence of the text structure is lexical cohesion, namely the dependency relationship between words based on associative relations in common knowledge. This thesis proposes an objective and computationally feasible method for measuring lexical cohesion, especially semantic relations, between words. Lexical cohesion between words is computed on a semantic network constructed systematically from a subset of an ordinary English dictionary. Spreading activation on the semantic network analyses the meaning of a word into a 2,851-dimensional semantic space and computes the strength of lexical cohesion between any two words in the dictionary. As an evaluation of the measurement of lexical cohesion, this thesis then presents a quantitative indicator, Lexical Cohesion Profile (LCP), for segme...

The ultimate---if implicit---goal of artificial intelligence (AI) research is to model the full range of human cognitive capabilities. Symbolic AI and connectionism, the major AI paradigms, have each tried---and failed---to attain this goal. In the meantime, the idea has gained ground that this goal might still be within reach if we could harness the respective strengths of these two paradigms in integrated neurosymbolic models. This paper attempts to lay a cognitive basis for neurosymbolic integration and describes the different strategies that have been adopted to date. Unified approaches strive to attain symbol-processing capabilities using neural network techniques alone, while hybrid approaches blend symbolic and neural models in novel architectures with the hope of gleaning the best of both paradigms. Keywords: Connectionism, symbolic AI, neurosymbolic integration, hybrid models, connectionist symbol processing 1 Introduction Since its inception, artificial intelligence (AI) ha...