| 
   
Article Details
Common Sense Advisory Blogs
Deep Web Implements the Multilingual Search that Google Imagines
Posted by Donald A. DePalma on December 17, 2009  in the following blogs: Web Globalization
Pages | |


In an interview with the U.K. newspaper The Daily Telegraph, Google vice president for search products Marissa Mayer challenged the readership to "Imagine what it would be like if there was a tool built into the search engine which translated my search query into every language and then searched the entire world's websites." We spoke with Abe Lederman, CEO of Deep Web Technologies, a technology supplier that already offers this multilingual search.

Mayer completed the vision of multilingual search with machine translation (MT) software delivering the content in your language: "And then invoked the translation software a second and third time – to not only then present the results in your native language, but then translated those sites in full when you clicked through."

Yes, we'd love to see that. In July 2005, we wrote that in our years of talking with enterprise search vendors:
"... one question [that] none of [the enterprise search vendors] could answer was 'what if there is an answer out there but it’s not in English? Could you do a cross-language search? Could you re-direct my English-language query about transmogrifying rectabular excrusions into the rich body of Albanian scientific literature on the subject? And while you’re at it, would you be so kind as to translate the Albanian documents into English on the return trip to my computer screen?' Okay, that’s four questions. This capability could dramatically increase the chance of finding something relevant to my needs."
In that post, titled "Parlez-Vous Deutsch?", we wrote about Yahoo!'s erstwhile work in translating queries for English, French, and German. Other firms have taken up the multilingual search challenge, but, until now, none in earnest.

In October 2009, we talked with Abe Lederman about Deep Web's integration of machine translation into its enterprise search engine. Earlier this month, we caught up with him as he returned from Online Information 2009 in London where he was on the lookout for new partners. Lederman showed us the multilingual search that his firm developed under contract to the Office of Scientific & Technical Information (OSTI) at the Department of Energy for WorldWideScience.org, "the global science gateway."

Clicking on the Advanced Search tab, we thought of the U.N. Climate Change Conference as we looked for "global warming." We limited our search to sources in the Czech Academy of Science, just two of the dozens of scientific sites from around the world in languages ranging from Chinese to Japanese to Russian. The first hit was an English-language paper on "Modeling mortality risks due to heat stress in East Asia" from the Czech Academy,  while the second was "Budeme žít v globálním Somálsku? : O klimatickém konci civilizace a strachu z katastrofy" ("will we live in a global Somalia? The climatic end of civilization and fear of disaster"). Being in a 2012 on-the-road kind of mood, we also looked for "pandemic" in a broader pool of sites, yielding French, Chinese, and Spanish articles (click here for a screenshot of our query results).

What happened behind the scenes? Deep Web translated the search terms into the languages of the sources, searched them, and returned some translated details. For the publicly available documents in the results, we could have used the built-in machine translation to read them. Deep Web currently supports both Google and Microsoft MT software. Beyond the MT queries and results, Deep Web clusters and ranks the results like any enterprise search engine, but with multilingual sources informing the results. There are still glitches at the WorldWideScience.org site, including the primarily English state of the user interface and the failure to translate some critical phrases such as "Klícová slova" ("keywords") in the results. Lederman tells us that he, OSTI, and the other WorldWideScience sponsors are discussing whether they should localize the interface.

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. OSTI will work with Deep Web and the World Wide Science Alliance to launch this multilingual search capability at the International Council for Scientific and Technical Information's (ICSTI) annual meeting in Helsinki in June 2010.

The bottom line: Multilingual search is not just a figment of Google's imagination. It’s already here -- you just have to dig a bit deeper to find it.

 

Post a Comment

Name
Email address :(Your Email Address Will Not Be Displayed)
URL

Your Comments
Enter Code given below :    

Link To This Page

Bookmark this page using the following link:http://www.commonsenseadvisory.com/Default.aspx?Contenttype=ArticleDetAD&tabID=63&Aid=634&moduleId=391

Do you have a website? You can place a link to this page by copying and pasting the code below.
Back
Keywords: Multilingual search, Multilingual search engine optimization, Web globalization

  
Refine Your Search
  Date
Skip Navigation Links.
Skip Navigation Links.




 
 
Terms of Use | Privacy Statement | Contact Us
Copyright © 2016 Common Sense Advisory, Inc. All Rights Reserved.