Automating knowledge acquisition for machine translation.(Natural Language Processing) From: AI Magazine | Date: December 22, 1997| Author: Knight, Kevin | COPYRIGHT 1997 American Association for Artificial Intelligence. This material is published under license from the publisher through the Gale Group, Farmington Hills, Michigan.  All inquiries regarding rights should be directed to the Gale Group.Copyright information

Machine translation of human languages (for example, Japanese, English, Spanish) was one of the earliest goals of computer science research, and it remains an elusive one. Like many AI tasks, translation requires an immense amount of knowledge about language and the world. Recent approaches to machine translation frequently make use of text-based learning algorithms to fully or partially automate the acquisition of knowledge. This article illustrates these approaches.

How can we w...

Related newspaper, magazine, and journal articles from HighBeam Research

	Automating knowledge acquisition for machine translation.(Natural Language Processing) AI Magazine ; ... it into logic or your favorite knowledge representation language. This conversion process will appeal to a dictionary, which maps words (such as canyon) onto concepts (such as canyon) and to a world model that contains facts about reality (such as canyons ... called CANDIDE. This system performs as well as the ...
	Easy Ways to Get It Almost Right International Herald Tribune ; Robert Youngblood International Herald Tribune 03-05-2001 Perfect translations by computer are nowhere in sight, but the existing technology has found a ready audience on the Internet, where widespread machine translation, however imperfect, is available in a variety of languages.Just don't expect
	Machine Translation: Is It Good Enough? e-Business Advisor ; ... categorizing, and routing text are readily available. That's good news. If the customer truly is king, then you should speak the king ... accuracy of translation, use a multilingual thesaurus that directly maps uncommon terms from a source to a target language. This lets ... Intelligent Miner for Text suite ... .
	Robot translators decipher mountains of enemy messages. Knight Ridder Washington Bureau (via Knight-Ridder/Tribune News Service) ; Byline: Robert S. Boyd WASHINGTON _ Somewhere in a vast jumble of documents in a Baghdad warehouse or in the constant buzz of electronic signals in the sky, a few ominous words or phrases may be hidden: Explosives. Nerve gas. Convoy. Airport arrival. The president. The words, however, are in
	Pros sort computer translating.(LIFE - SCIENCE & TECHNOLOGY) The Washington Times ; ... Arabic are the top languages with which they work, but Spanish and Korean also are used. The documents involved include broadcast news as well as print forms of communication. Interestingly, Arabic and Spanish have more in common structurally than I realized ...
	Big leap in machine language translation International Herald Tribune ; 00-00-0000 Statistical machine translation ã in which computers essentially learn new languages on their own instead of being ''taught'' the languages by bilingual human programmers ã has taken off. The new technology allows scientists to develop machine translation systems for a wide
	What's new in machine translation? Communication World ; Caaterpillar Tractor, the Illinoisbased industrial machinery giant, sells all over the world. Yet even with all their capabilities, Caterpillar's severely handicapped in their marketing ability. Why? Currently, they are able to translate a paltry five percent of what they would like to, and more
	Demand for computer linguists up The Milwaukee Journal Sentinel ; ... linguists up Many companies want more sophisticated Web options beyond simple translations By PATRICIA V. RIVERA Dallas Morning News Monday, February 10, 2003 Need efficient computer software to translate an employee manual into 60 languages? Or a program that ...
	An overview of empirical natural language processing.(Natural Language Processing) AI Magazine ; One of the biggest challenges in natural language processing is how to provide a computer with the linguistic sophistication necessary for it to successfully perform language-based tasks. This special issue presents a machine-learning solution to the linguistic knowledge-acquisition problem: Rather
	Computer linguists mix language, science. The Dallas Morning News (via Knight-Ridder/Tribune News Service) ; ... machine translation, information retrieval, speech processing and text mining. ___ (c) 2003, The Dallas Morning News. Visit The Dallas Morning News on the World Wide Web at http://www.dallasnews.com/ Distributed by Knight Ridder/Tribune Information Services ...

See all results.