In this paper, a supervised learning system of word sense disambiguation is presented. It is based on conditional maximum entropy models. This system acquires the linguistic knowledge from an annotated corpus and this knowledge is represented in the form of…

An increasing number of organizations are involved in the development of strategic
information systems for effective linkages with their suppliers, customers, and other
channel partners involved in transportation, distribution, warehousing and maintenance
activities. An efficient inter-organizational inventory…

PATN is a design for a machine problem solver which uses an augmented transition network (ATN) to represent planning knowledge. In order to explore PATN's potential as a theory of human problem solving, a linguistic approach to protocol analysis is…

by Jose Maria Gonzalez Pinto., Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2002., Includes bibliographical references (p. 68-69).

This paper presents and analyzes the influence of chronological distance between an original medieval text and its translation on the type of translation and the translation strategies –modernization/arcaization and philological/communicative translation– followed by a contemporary translator. Extracts of the medieval…

After considering the various dimensions of innovation policy, this paper reviews the experiences of the Czech Republic (CR) in implementing such policies in the post-1990 transition period. Particular attention is paid to the contribution of small and medium-sized enterprises (SMEs)…

Short survey carried out at the beginning of the course in order to elicit information about the students' background, future prospects and knowledge of ICT.

A grande maioria dos Sistemas de Gerenciamento de Aprendizagem predominantemente em uso no ensino com suporte computacional são estáticos e lineares, ou seja, apresentam o mesmo conteúdo instrucional para os diversos estudantes sem considerar o nível de aquisição de conhecimentos…

Most neural network learning algorithms cannot use knowledge other than what is provided in the training data. Initialized using random weights, they cannot use prior knowledge such as knowledge stored in previously trained networks. This manuscript thesis addresses this problem.…

This paper present the structure, function and performance of SPOST, a broad coverage, rule-based part-of-speech tagger developed as a component of the Pagnlyzer Spanish Analysis Component of the Pangloss Knowledge-based Machine Translation System. It also describes preparations for the general…