On ZDNet: Where are these Microsoft patches?
Find Articles in:
all
Business
Reference
Technology
News
Sports
Health
Autos
Arts
Home & Garden
advertisement
advertisement

Content provided in partnership with
Thomson / Gale

Business Services Industry

Language Weaver CTO Says Improvements to Statistical Machine Translation Expand Opportunities for Government Customers

Business Wire,  July 9, 2008  

LOS ANGELES -- Language Weaver Co-Founder and Chief Technology Officer Daniel Marcu said today that rapid advancements in the field of software-based statistical translation are providing government customers with a range of new, more powerful translation solutions.

Language Weaver, the leader in statistical software-based language translation solutions for the enterprise, provides automated translation solutions for a variety of government organizations.

In a podcast interview available for listening and download at Language Weaver's blog at blog.languageweaver.com, Marcu said that both the speed and accuracy of statistical translation systems have improved exponentially in the past 10 years. He also explained how Language Weaver is working to further improve the applicability of its proprietary translation technology.

"At the time I entered the statistical machine translation field in the late 1990s, statistical machine translation systems were able to translate documents at the speed of one document per day. Today, we've reached the point where we translate between 2,000 and 5,000 words per minute on a single CPU."

Marcu said that due to the advantages of statistical machine translation over conventional rule-based systems, there are no insurmountable barriers for developing and continuously improving software-based translation systems. Language Weaver is now working to increase quality for wider applicability across a range of government and commercial initiatives.

For example, "At Language Weaver, we figured out how, with reasonable investments, we can build statistical machine translation systems for what we call 'less commonly taught languages,' or low density languages," said Marcu.

Other initiatives include the introduction of syntax and semantics, along with adding more ways for the user to interact with the system in a straightforward, easy manner.

"The most important change is that our government and commercial clients move from asking the question, 'Can we build this machine translation system?' to, 'do the market's needs justify the development of it?'"

Listen to entire interview with Language Weaver Founder and CTO Daniel Marcu at blog.languageweaver.com.

About Language Weaver, Inc.

Language Weaver was founded in 2002 to commercialize a unique approach to automatic language translation using proprietary statistical translation algorithms that resulted from research and development at the University of Southern California's Information Sciences Institute (USC/ISI). Language Weaver's translation systems produce fluent, natural sounding translations and save customers money and time through automation of the translation process. Learn more at www.languageweaver.com.

COPYRIGHT 2008 Business Wire
COPYRIGHT 2008 Gale, Cengage Learning