|Google files patent to serve translated documents for foreign searches|
| 5:45 pm on May 8, 2009 (gmt 0)|
CROSS-LANGUAGE SEARCH [appft.uspto.gov]
as i understand it, google will decide to serve a foreign language result if the algo can't identify a document, which is deemed of sufficient quality and relevance, written in the queries native tongue.
|For example, if a user in Egypt enters a query in Arabic for a subject such as American football, there might not be many web pages in the query language that provide relevant results for the query. However, there may be relevant pages in other languages. For example, the Arabic query from the previous example can be translated to an English query, and compared to an English index of web pages. If there are more relevant results found among the web pages in the English language in this example, a list of relevant pages can be translated and provided to the user. |
it appears google will hold a translated document to a higher relevance score than a document written in the native language in which the query is written. hence...
|In some implementations, the respective relevance scores associated with the results of the translated search query (Q') 50a can be compared to a relevancy score threshold to determine whether to serve a translated web page as a result to the search query (Q) 20a. For example, in some instances the results of the translated query (Q') 50a might have such low relevance scores that they will not be served to the searcher, even if the results of the translated search query (Q') 50a have a higher relevance scores than the results of the search query (Q) 20a. |
i am thinking it will be easier to optimize a site on a foreign tld which is hosted on a foreign server that will not require high relevance and confidence scores to out rank a translated competitor.
|In these examples, the tokens included in a search query or a translated search query that match an entity (e.g., local or foreign) can be identified using an encyclopedia website associated with the first language or the second language, respectively. In other examples, location servers can be used to identify locations associated with the search query or the translated search query. |
i would write content on that foreign tld in its native language, and write translated versions in languages spoken in countries to which the query would be mostly associated.
| 9:27 pm on May 9, 2009 (gmt 0)|
I don't recall being served any pre-translated results so far, so I'm not sure how widely employed this approach currently is. Given the awkwardness of machine translation, I'm not sure that ranking well through this approach would translate into traffic that has true business value.
| 9:37 pm on May 9, 2009 (gmt 0)|
It's shocking what one can patent in the US.
| 10:31 pm on May 9, 2009 (gmt 0)|
|I don't recall being served any pre-translated results so far |
i have seen English results served for Spanish queries, and the option to translate some pages. i am thinking it would be mostly applied to languages foreign to English.
| 10:32 pm on May 9, 2009 (gmt 0)|
|It's shocking what one can patent in the US. |
well it hasn't been granted yet.
| 11:46 pm on May 9, 2009 (gmt 0)|
|...as i understand it, google will decide to serve a foreign language result if the algo can't identify a document, which is deemed of sufficient quality and relevance, written in the queries native tongue. |
Interesting. I experienced this about six weeks ago. Couldn't make sense of it when doing long tail searches for my own site.
Instead of my pages showing up on results, let's say 20-50, all I got were Asian language pages - and across many tld's in the region!