The goal of the PANGLOSS projecd is to develop a system which will, from the very beginning, produce highquality translations of unconstrained text. This can only be attained currently by keeping the human in the translation loop, in our case via a software module called the A U O ~ R . The main measure of progress in the development of the Pangloss system will therefore be the gradual decrease...

This paper describes efforts underway to construct a largescale ontology to support semantic processing in the PANGLOSS knowledge-base machine translation system. Because we axe aiming at broad sem~tntic coverage, we are focusing on automatic and semi-automatic methods of knowledge acquisition. Here we report on algorithms for merging complementary online resources, in particular the LDOCE and ...

The goals of the PANGLOSS project are to investigate and develop a new-generation knowledge-based interlin-gual machine translation system, combining symbolic and statistical techniques. The system is to translate newspaper texts in arbitrary domains (though a specific financial domain is given preference) to as high quality as possible using as little human intervention as possible. The projec...

Pangloss is a new knowledge-based machine translation project carried out jointly by the Center for Machine Translation at Carnegie Mellon University, Computing Research Laboratory of New Mexico State University and Information Sciences Institute of the University of Southern California. One of the distinguishing features of systems built in this project is that they uniformly aim at high-quali...

Although automatic machine translation (MT) of unconstrained text is beyond the state of the art today, the need for increased translator productivity is urgent. The PANI3LOSS system addresses this dilemma by integrating MT with machine-aided translation (MAT). The main measure of progress in the development of the PANGLOSS system is a gradual increase in the level of automation. The current PA...

The Pangloss Example-Based Machine Translation engine (PanEBMT) 1 is a translation system requiring essentially no knowledge of the structure of a language , merely a large parallel corpus of example sentences and a bilingual dictionary. Input texts are segmented into sequences of words occurring in the corpus, for which translations are determined by subsentential alignment of the sentence pai...

Sharing knowledge across projects is often considered impossible, especially if the systems involved present differences in underlying theory, representation, or even programming language. This paper, taking a collaboration between the CAT2 and PANGLOSS MT projects as an example, demonstrates that it is possible to combine resources developed separately to support the processing of different mo...