Deep Web Technologies to unveil multilingual federated search in June | Federated Search BlogFederated Search
23
Dec

Multilingual federated search is a big deal for a couple of reasons. First, no one has done it up to now. Yes, Google just added translation into its universal search. And, no doubt Bing will follow suit. But, being able to search the quality scientific and technical information that sometimes is only available via federated search, and doing it in foreign languages, is important.

The second reason that multilingual federated search is so important is because China, Japan, Russia, and other nations produce large volumes of research output. As the world shrinks we can’t afford to ignore the non-English literature. In a blog article the author noted that Thomson Reuters highlighted the importance of China’s research output on the basis of sheer volume :

According to citation analysis based on data from Web of Science, China is ranked second in the world by number of scientific papers published in 2007. Scientific’s World IP Today Report on Global Patent Activity 2007 reported that China almost doubled its volume of patents from 2003 to 2007, and looks set to become a strong rival to Japan and the United States in years to come.

The bottom line: federated search is about research and research is global.

Blog sponsor Deep Web Technologies has developed a multilingual version of its Explorit federated search application. And, they have partnered with the US Department of Energy’s Office of Scientific and Technical Information (OSTI) to introduce multi-lingual searching to the global science gateway, WorldWideScience.org.


Click image to enlarge.

Deep Web Technologies first announced multilingual searching in a September press release:

SANTA FE, N.M., Sept. 3, 2009 — Deep Web Technologies is proud to announce development of a prototype of a multilingual translation capability for clients using its federated search applications. An early prototype of multilingual searching was demonstrated to the members of the WorldWideScience Alliance in June of 2009. This new feature, when fully developed and implemented, will translate a user’s search query into the native language of the collections being searched, will translate result titles and snippets back to the user’s original language and aggregate and rank these results according to relevance. The translation process will be seamless, making it simple to search collections in multiple languages from a single search box in the native language of the user.

The press release further notes:

While many countries have a wealth of research content in local collections, much of this information has not been translated to other languages. Deep Web Technologies’ multilingual translation capability will augment the Explorit Research Accelerator(TM) federated search engine, allowing users to search multiple collections from different countries and languages simultaneously. The current prototype provides for searches of collections in English, Spanish, German, French, Portuguese, Russian and Chinese where the user selects the language desired for the results, which are aggregated, deduped, ranked and clustered in the selected language.

Common Sense Advisory’s Chief Research Officer Don DePalma was the first to announce to readers of Global Watchtower last week that Deep Web Technologies will be unveiling its multilingual federated search technology next June. Don DePalma has more than 25 years of experience in the fields of technology, language services, and market research. He closely watches developments in global business and in globalization.

DePalma’s article tells of the vision that led to the creation of WorldWideScience.org.

OSTI Director Dr. Walt Warnick first introduced the concept of the global science gateway in 2006 and worked to to establish single-query search of English-language national databases from 61 countries encompassing over 400 million “pages of science.” Advancing the notion that “the diffusion of scientific knowledge will accelerate scientific progress itself,” Warnick pushed for multilingual translations at WorldWideScience.org, first realizing the vision in June 2009 through the Deep Web implementation.

The multilingual version of WorldWideScience.org will be launched in June at ICSTI’s 2010 Summer Conference in June in Helsinki. ICSTI, the International Council for Scientific and Technical Information, is a primary sponsor of the WorldWideScience.org Alliance. The Alliance “provides a geographically-diverse, governance structure to promote and build upon the original vision of a global science gateway.”

[ Disclaimer: I consult for OSTI and for Deep Web Technologies. ]

If you enjoyed this post, make sure you subscribe to my RSS feed!

Tags:

This entry was posted on Wednesday, December 23rd, 2009 at 2:41 pm and is filed under multilingual, technology. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or TrackBack URI from your own site.

Leave a reply

Name (*)
Mail (*)
URI
Comment