Printer Friendly

CARNEGIE GROUP SIGNS CONTRACT WITH CATERPILLAR FOR DEVELOPMENT OF A FULLY AUTOMATIC TEXT TRANSLATION SYSTEM

 CARNEGIE GROUP SIGNS CONTRACT WITH CATERPILLAR FOR DEVELOPMENT
 OF A FULLY AUTOMATIC TEXT TRANSLATION SYSTEM
 ATLANTA, May 8 /PRNewswire/ -- Carnegie Group, Inc., and Caterpillar, Inc. (NYSE: CAT) announced today a multimillion-dollar, five-year project to develop a fully automated machine translation system for Caterpillar's technical documentation.
 The Automated Machine Translation (AMT) system, being developed with Carnegie Mellon University's Center for Machine Translation, will completely automate the translation of millions of pages of manuals distributed internationally by Caterpillar for its equipment. The system will eliminate the need to post-edit machine-generated documents in any of 11 major languages.
 The advanced technology AMT system is being demonstrated at Carnegie Group's booth (No. 106) at the Society for Technical Communications 39th Annual Conference and Exposition, being held in Atlanta's Peachtree Center Exhibit Hall from May 9-12.
 Caterpillar, based in Peoria, Ill., initiated the AMT project to facilitate its global operations and to comply with the European Economic Community's (EEC) recent directive stipulating that all operations manuals for equipment and hardware shipped into EEC countries after 1992 must be written in the user's native language. Caterpillar's complete set of manuals consists of more than 2 million pages of text which are ultimately translated into 35 target languages.
 Caterpillar will implement the AMT system over a period of five years and will use it to translate all operations and technical manuals that support the company's extensive line of equipment. Caterpillar is the world's largest manufacturer of earth-moving equipment and a major manufacturer of diesel, natural gas and turbine engines.
 Traditional machine translation systems have attempted to translate text using all possible English words and rules of grammar. These systems tend to be prone to errors because they lack technical domain knowledge. As a result, output from these systems requires post-editing by human translators, which is expensive and time-consuming.
 The AMT system, which runs on standard computer workstations, uses a revolutionary approach to the translation problem. A form of Knowledge-based Machine Translation (KBMT), this method, developed at CMU, relies on a restricted domain of subject matter, in this case, the domain of Caterpillar service information, coupled with a limited vocabulary and syntax. The vocabulary and syntax define a subset of English, called Caterpillar Technical English (CTE). Carefully designed to allow complete expression of the clear and concise documentation that accompanies Caterpillar's equipment, CTE fully satisfies the needs of technical writers.
 "Although they do not hamper the writing of documentation, these restrictions allow us to eliminate the ambiguity normally inherent in the English language through a process of machine-encoding the knowledge domain," said Phil Hayes, director of Natural Language Systems at Carnegie Group. "Ambiguity is what causes the errors that require post-editing of traditional machine translation output. So by eliminating the ambiguity, we eliminate the need for post-editing."
 CTE documents are passed to the KBMT parser, which analyzes the text to product a semantic representation, querying the author, if necessary, for additional clarification. Each target language has an associated KBMT Generator, which produces the target language translation.
 AMT is designed to handle the special cases that arise in translation, like idiomatic expression, appropriate verb use, the expression of concepts where no literal translation exists and euphonic adaptation.
 Carnegie Group is the industry leader in applying advanced software technology to capture knowledge assets in semi-custom solutions. Through the automation of complex decision support for the telecommunications, discrete manufacturing, government, high technology, transportation and steel industries, Carnegie Group helps clients leverage their intellectual capital. Carnegie Group's technology is applied in the areas of configuration/provisioning, logistics/planning/scheduling, text processing, help desks/diagnostics, design for manufacturability and sales support/negotiation. Established in 1984, Carnegie Group currently employs more than 175 people.
 -0- 5/8/92
 /CONTACT: Jennifer Ace of Carnegie Group, Inc., in Pittsburgh, 412-642-6900, or Sharlene Gallup of Caterpillar, Inc., in Peoria, Ill., 309-675-7342/
 (CAT) CO: Carnegie Group, Inc.; Caterpillar, Inc. ST: Pennsylvania, Illinois IN: CPR MAC SU: CON


DM-KD -- PG007 -- 8188 05/08/92 15:26 EDT
COPYRIGHT 1992 PR Newswire Association LLC
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 1992 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Publication:PR Newswire
Date:May 8, 1992
Words:658
Previous Article:MEDIQ REPORTS SECOND QUARTER RESULTS
Next Article:PAI GOW POKER 'EXPERIMENT' BEGINS IN ATLANTIC CITY
Topics:


Related Articles
ACME STEEL AWARDS CONTRACT TO SMS SCHLOEMANN-SIEMAG, CARNEGIE GROUP, INC. AND COMPUTER TASK GROUP, INC.
CARNEGIE MELLON LICENSES ITS LYCOS(TM) INTERNET WEB CATALOGING SOFTWARE TO NLIGHTN
CARNEGIE GROUP, INC. DELIVERS OPERATIONAL PROTOTYPE TO US TRANSPORTATION COMMAND (USTRANSCOM)
CARNEGIE GROUP AND I2 TECHNOLOGIES ANNOUNCE FIRST-EVER INTEGRATED SCHEDULING SOLUTION
U.S. ARMY USING CARNEGIE GROUP SOFTWARE TO SUPPORT BOSNIAN PEACE-KEEPING EFFORT
IPSCO INC. LOOKS TO CARNEGIE GROUP FOR INNOVATIVE APPROACH TO SCHEDULING AND PRODUCTION
U S WEST Communications and CGI Announce Deployment of a Call Handling System
Intelligent Systems Integration Services from Carnegie Group, Inc. to Enhance HSII IDS Capabilities; Healthcare Systems Developer Will Use CGI...
Carnegie Group and Versatility Partner to Service Call Center Customers
Genesys and Carnegie Group Partner to Service Call Center Customers

Terms of use | Copyright © 2016 Farlex, Inc. | Feedback | For webmasters