Microsoft Research to enhance multilingual content with Wikipedia

by CXOtoday Staff    Oct 19, 2010

multilingial210Microsoft Research launched of the beta version of WikiBhasha, a multilingual content creation tool for Wikipedia. The tool is meant to enable Wikipedia contributors to find content from other Wikipedia articles, translate it into other languages, and then either compose new articles or enhance existing articles in multilingual Wikipedias. Microsoft Research conducts both basic and applied research in computer science and software engineering.

“We’re always happy to see work on improving multilingual collaboration between wikis,” commented Danese Cooper, CTO of the Wikimedia Foundation.

The WikiBhasha beta is available as an open source MediaWiki extension, under the Apache License 2.0, and as a user gadget in Wikipedia. The tool is also available as an installable bookmarklet on a site hosted on the Windows Azure platform from Microsoft. WikiBhasha will support content creation in more than 30 languages. Initially, the Wikimedia Foundation and Microsoft Research will also work closely with the Wikipedia user communities focusing on content creation in Arabic, German, Hindi, Japanese, Portuguese and Spanish.

“The WikiBhasha beta holds the promise of enabling easy creation of content in multiple languages, and also of generating a large body of parallel language data for researchers to work on to further machine translation technology,” remarked P. Anandan, MD, Microsoft Research India.

The WikiBhasha beta currently works on Windows Internet Explorer (7.0 and 8.0) on Windows XP, Windows Vista and Windows 7, and on Firefox (3.5 or above) on Linux Fedora (11 and 12), Windows XP, as informed by the company.

The tool features a user interface (UI) layer that stays on the target-language Wikipedia for the entire content creation process. This UI layer integrates content discovery with linguistic and collaborative services, focusing the user primarily on content creation in the target Wikipedia.