[ale] language(locale) detection in gmail

Jerry Yu jjj863 at gmail.com
Fri Oct 6 10:44:11 EDT 2006


 Bj?rn had similar experience with Swedish vs. related scandinavian
languages.

On 10/6/06, Bj?rn Gustafsson <bjorng at gmail.com> wrote:
>
> The short answer is that they don't detect the encoding.  At most they
> will look at the mail header to find the Content-Type, which shows the
> encoding.  Then Google does its standard pattern-matching to find ads
> with related keywords.
>
> I see this a lot when I get emails in Swedish: the ads are always in
> related scandinavian languages.
>
> On 10/6/06, Jerry Yu <jjj863 at gmail.com> wrote:
> > Reading an email in Chinese, I noticed that all sponsored links served
> by
> > gmail are in Japanese. With my limited Japanese training (one year in
> > college), I can tell the links, albeit in wrong language, are actually
> > pertinent to the content of  the email.
> > This comes to a question, anybody know how google,or anybody for the
> matter,
> > detect the locale (charset encoding?), given a chunk of text?
>
-------------- next part --------------
An HTML attachment was scrubbed...




More information about the Ale mailing list