The Workstation Substrate of the Pangloss Project

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-quality output and broad coverage while accepting that full automation under such conditions is not immediately attainable. As a result, Pangloss systems rely on humancomputer interaction during processing. This interaction must be supported by appropriate computer environments. There are two major kinds of people for whom environments can and must be constructed — developers and end users. Developers need help with a variety of knowledge acquisition tasks, such as dictionary and grammar writing. End users (e.g., technical writers, translators or editors of machine translations) look for efficiency enhancements beyond the level of word processing support. There are two approaches to building interactive tools. A dedicated workstation can be developed for each of the required functionalities. Alternatively, workstations can be configured as sets of application routines attached to a universal user interlace. In this paper we describe a user environment for Pangloss. It can support several machine-aided human translation configurations and a human-aided machine translation configuration, It also supports knowledge acquisition for machine translation and other NLP systems.