Document clustering based on semantics is a fundamental method of helping users to search and browse in large collections of documents. Recently a number of papers have reported the applications of self-organizing artificial neural networks in document ...

The paper considers conjunctive and disjunctive version space learning as an incomplete search in complete hypotheses spaces. The incomplete search is guided by preference biases which are implemented by procedures based on the instance-based boundary ...

The paper describes the recognition of diphthong and triphone signs useful in automatic generation of English text from Pitman Shorthand Language (PSL) document. The PSL is used to note down the dictated/spoken text and is widely practiced in all ...

This paper has two main objectives. One is to show that the dynamic knowledge representation paradigm introduced in [ALP+00] and the associated language LUPS, defined in [APPP99], constitute natural, powerful and expressive tools for representing ...

In this paper we present CoHyDe (Collaborative Hypermedia distributed Design), an open and strongly distributed hypermedia model that supports distributed workgroups. The architecture is based on the metaphor of the actor model and is structured in ...

The Davis and Putnam (D&P) scheme has been intensively studied during this last decade. Nowadays, its good empirical performances are well-known. Here, we deal with its theoretical side which has been relatively less studied until now. Thus, we propose ...

This paper presents the design and currently elaborated components in the knowledge-basedl earning environment called STyLE. It supports learning of English terminology in the domain of finances with a target user group of non-native English speakers. ...

We present in this paper our reflections about the requirements of new architectures and languages for the Web, confronted with the ones emerging from qualified scientists such as Mc Carthy [1] and Wegner [2]. The contribution highlights if and how ...

In the present paper we use the approach of height functions to defining a semi-distance measure between Horn clauses. This appraoch is already discussed elsewhere in the framework of propositional and simple first order languages (atoms). Hereafter we ...

The paper discuses some problems of presentation and processing of linguistic knowledge, needed for the development of real-size Bulgarian linguistic resource to be used in a multilingual text generation system, covering software manuals sublanguage. ...

An approach for the usage of metaphors in learning terminology in a foreign language is presented. The approach integrates ideas from the metaphor theory of Lakoff and Johnson [6] with techniques from corpus-based computational linguistics, advanced ...

By the expert information we mean the information given by a man-expert of a field of science and technology, or by some intelligent program (for example intelligent agents) in solving of some task. We assume that in an intelligent distributed system ...

Scheduling is an important aspect of automation in manufacturing systems. It consists in allocating a finite set of resources or machines over time to perform a collection of tasks or jobs while satisfying a set of constraints. One of the most known and ...

In this paper we describe first the nature of laws and regulations, which are not-normal, fragmented pieces of text, that can only be understood by using some (implicit) model about the world to be regulated. Then we describe the process of drafting ...

A two-layer Recurrent Neural Network Model (RNNM) and an improved Backpropagation-through-time method of its learning are described. For a complex nonlinear plants identification, a fuzzy-neural multi-model, is proposed. The proposed fuzzy-neural model, ...

Control of Systems in different real world fields such us Chemistry, Medicine, Robotics, etc. has been tackled for decades with approaches developed in the classical Control Systems field. In this paper, we will propose a Real Time controller relying on ...

This paper presents an effective system for recognizing the identity of a living person on the basis of iris patterns that is one of the physiological and biological features with high reliability. To represent the iris pattern efficiently, a new method ...

We present a sound and complete, tractable inference method for reasoning with localized closed world assumptions (LCWA's) which can be used in applications where a reasoning or planning agent can not assume complete information about planning or ...

The main operators in Inductive Logic Programming (ILP) are specialization and generalization. In ILP, the three most important generality orders are subsumption, implication and implication relative to background knowledge. The present paper discusses ...