How Language Search at Google may work
Imagine that you want to cook a Chinese meal from an authentic Chinese recipe. Your search for the recipe in Google by the English name of the dish, and the search engine translates your query into Standard Mandarin, performs the search and finds some recipes in that language, and returns those pages to you with an option to translate them into English.
Or, you have an assignment for your philosophy class, and you want to write a paper on Benedetto Croce and his Philosophy of Spirit. You’ve read some papers on him published in English but would like to find some in Italian.
You go to Google and choose “Italian” as a language that you would like to see source pages from as you enter his name into the search box. The search engine looks through Italian language results that contain the name Benedetto Croce, finds many results, and provides page titles and snippets that it finds. Clicking on a “translate” link next to the title to one of those pages will bring you the page translated into English.
Perhaps you’ve decided that you want to start biking to work instead of commuting by car, and you want to learn more about biking and bicycles. You enter a search into Google for the word [biking], and the search engine looks at statistical associations that it has created between keywords and Web content, and not only returns results to you for [biking] but also for the word [cycling].
A Google patent application published this week describes an expanded language search engine, which might enable you to search for pages in other languages using translations of the queries you search with. It might also enable you to receive additional results in your language for words that are statistically related to your query terms in a meaningful way, like “biking” and “cycling.”
I wrote a post a few weeks back about another Google patent filing that described how Google might find synonyms for search queries using a statistical machine translation approach.
The expanded language approach to searching is described in:
Automatic Expanded Language Search
Invented by Johnny Chen
Assigned to Google
US Patent Application 20090024595
Published January 22, 2009
Filed July 20, 2007
A computer-implemented method can include translating a search query from a first language to a second language, comparing the translated query with content in the second language, and identifying content in the second language relevant to the translated query based on the comparing.
Also, a computer-implemented method can include translating content in a second language at one or more network locations into a first language, comparing the translated content with a search query written in the first language, and identifying, from the translated content, content relevant to the query based on the comparing.
The patent application tells us that the search engine might look for results in other languages if those are specified by a searcher, or it might return pages in other languages based on some other factors, such as:
- The popularity of the language,
- Attributes of the user,
- Search history,
- Relevance to the subject matter of the query,
- The character type entered by the searcher (e.g., Chinese characters, Greek characters, etc.),
- The browser’s language settings,
- The domain of the search engine (e.g., google.cn for Chinese, google.tw for Taiwan-Chinese, etc.),
- User input, and;
- Other factors.
While a searcher might be able to choose to see search results from pages in other languages, if they don’t and there aren’t many results for their query, and one reason might be related to the language of that query (such as the name of a Chinese dish that might not be very popularly known in English), the search engine might be set up to expand the languages used in choosing results.
Last Updated July 4, 2019.
21 thoughts on “Google to Expand Language Search and Shrink Our World?”
It would be interesting to see the development of this idea; however, I think most of us are aware of the fact that automated translation programs rarely capture nuances from one language to another. I have stopped using the translate option on pages where I can read the original language, because I find that I obtain a good deal of gibberish. My son is learning how to play the viola, and he is peppering me with questions about classical music. He brought up the piece by Mozart “Eine kleine Nachtmusik”, which has been typically translated as “A Little Night Music”, and since the play has had certain sexual connotations. The German word “Nachtmusik” actually translates to the English “Serenade”. In fact, Germans have five words for the English word. Mozart’s intention was to indicate that this piece was a serenade that was going to be played at night, instead of “Abendmusik”, a serenade to be played in the evening, and so on. Although Mozart’s humor may have enjoyed the implication that his title has spawned in English, that intention is never given in the German. In a case like this, Google has to understand the intention/understanding of the user and how that relates to the language being searched.
This could be a very interesting offering. That said I think it’s best application would be across a single language offering results for synonyms. Often for fun we run content through translation programs and back again just to see how far from the original we can get. Until a machine can translate someone relatively close to actual intent I don’t see how this would work.
But as with so many applications, it’s not what it does but what it could actually be used to do.
Thanks for the illustration of problems that Google’s translation may run into. Machine translation still does have a long way to go. I do expect that this is an area that Google will be spending a lot of time trying to get right – they seem to be dedicated towards improving their translations.
Those are really good points. I think that right now, identifying synonyms in a single language is easier than finding relevant pages in other languages. The potential to do that is intriguing though.
I personally like this idea…I already actually use the translation engine and to find articles within some of the niche markets I’m in in another language.
Hope it will take long for this to implement or else I’ll lose one cutting edge over my competitors 😀
Kidding…anyway as the guy who first commented said the translation engine is still far from perfect.
After all this would benefit all…after all, William, don’t you want to see native Italians reading your blog? 😀
I looked at the positive side of the implementation first and it’s quite impressive. But Frank’s opinion sounds interesting too. Two sides of the coin again!
Perhaps it is not a big deal for an ordinary internet surfer but for others, it might be a big feature and thing. Many years ago, I read an article on searching the stuff in an efficient way and I knew who different Big G is for an ordinary and well informed internet surfer.
I have never used translation services much either. Babble Fish was fun for about 5 seconds.
Although, I do use sites that have an audio pronunciation tool for foreign words. It would be neat to see this in a translation tool or search engine. Where you would click on any word in the foreign language and the search engine would provide an audio pronunciation for that word.
Thanks. I like the idea, though I think the potential implications might be a little beyond what I’ve expressed here. I’ve used Google”s translation engine to find articles in other languages as well. There are a lot of possibilities that open up when we can search and find relevant articles in other languages more easily. As Frank notes though, it’s going to open up some possibilities of misunderstanding as well. It will be interesting.
Yes, it is impressive. And I like looking at the positive sides of things. I think that it has the potential to create new conversations. I wonder how ready we are for those conversations.
I’m thinking of the possibilities that an expanded language search might open up for students and teachers and researchers and many others, and I think that it could allow people who share common interests but not a common language to share ideas and communicate. That would be a pretty big deal for everyone, I think.
Hi People Finder,
Interesting idea. I can see how Google might develop something like that based upon some of the pieces of what they are doing right now. The translate tool in the Google Toolbar does let you hover over words on a page in another language and get a toolbar tip translation. Google’s phone search (GOOG 411) is helping the search engine learn language modeling, at least for English right now, on a very large scale. Chances are that they would expand phone search to other languages as well. Combining the two could lead to what you suggest…
William Slawski, In the scenario, You are very right. I withdraw a part of my statement. I was only talking about using Google in the right way, perhaps in more sophisticated way.
Good points. There are lots of extra features and services that you can use on Google that many people probably aren’t taking advantage of, from searching for phrases by putting quotes around them, to using a “site:” operator to search for pages only from a specific site to more.
I still think that this expanded language search could be a very big addition to all of those other advanced search operators. I’d like to see it come out sometime soon, even if they offer it first in Google’s experimental search section first.
I never used translation services before but i am using Word web it’s a dictionary which has some of these services pronunciation.But the article is interesting and informative
Thanks for info
I agree that in any discussion of new technologies, the practical limitations of computing and resource usage needs to be considered.
We know that Google has been actively engaged in providing translation services, and in providing search to many different audiences speaking many different languages. I think that an expanded language search might be a natural outgrowth of the technologies that Google is developing anyway, but I imagine that it is computationally expensive.
It’s interesting that a number of the patent filings that have been coming out from Google (and other search engines) focus upon the technology behind the search engines, such as data center cooling, and how servers are used. What might not be possible today based upon cost and resources may be possible tomorrow.
In opinion this is a good idea from Google. But, they should also think of that this translation activity should not affect the normal search (English). Bcoz most people can read and understand english than any other language. Why i would say this, bcoz most people like to have websites with english content. If a people like to have his/her own language result he usually goes to his country related search engine.
So, if this new translation implementation get’s top over the normal search, then this will give a bad impression on Google.
I’m not sure that Google would attempt to implement something like this if it caused some serious problems to the relevancy of the search results that people see. I’d imagine that they would attempt to test it pretty thoroughly before using it on a wide scale.
It is something that I would really like to see, though. 🙂
When we used Google translation that translation not proper. Frank already emphasize that problem & that the main problem when we used Google translation.
Machine translation is definitely still a work in progress, as is search. It does look like Google is spending a considerable amount of energy and effort working upon it. A Telegraph UK article from last month emphasizes that in the words of Google’s Marissa Mayer:
English is a commercial lingua in many parts of the world, but English alone is no longer sufficient for global professionals who must compete and collaborate in a global economic environment. The need for Americans who can communicate in a second language and operate within another cultural frame of reference .And they need tools to make me understand?
I do think there’s a great benefit to all of us in the ability to perform searches and find relevant information regardless of what language it’s published in.
While I agree with you that it can be very helpful to communicate in more than one language, I’m not sure that is a problem that is being raised or addressed by this patent.
I think this technology will be good for the website owners who don’t have enough money to translate their websites from Chinese, French etc to English. These websites miss out on lot of traffic.
Although I agree with some comments posted earlier that Google does not translate the webpages properly in other languages. This is something they need to work on.
I suspect that many site owners don’t anticipate or expect visitors to their sites that don’t speak their language, and may not be too concerned about traffic from those visitors or they would have provided versions of their pages in other languages, and perhaps took into account different cultural elements associated with those visitors as well.
Not so much a matter of being unable to afford a translation service, but rather in many cases a business or marketing model that focuses upon people from a particular area that speak a particular language.
I added the Google translate widget to this site after seeing my site mentioned in a number of different languages, and statements from people wishing that my pages were availabe in French and German and Italian, and other languages. It really would have been too much work to provide those translations, and it would be difficult for me to work with clients who might not be too proficient in English, but I thought the widget might help some of those visitors, and I see from my log files that it is often used frequently.
Comments are closed.