Does somebody know why is this? Some poor algorithm, inability to learn as it grows, or what...?
- E.g. there is a 99% probability that sites from .rs domains will be in Serbian, unless they're in English or let's say German, French... But even there it poorly fails - says page is in Croatian ?! - also, some words are certanly Serbian if they're in a shorter form *(e.g. if Belo - white, then 100% Serbian if we only compare these two languages. Croatian is bijelo. Although there are parts of Serbian where they say bijelo, this only means that "bijelo" can be both Serbian or Croatian, but belo is 100% Serbian...* - even on non-local domains, it really isn't so difficult to distinguish between these two languages, - and in the beginning I was so frequently clicking on that link where you report it's not the correct language, and was suggesting Serbian, but in the end I gave up - when I see the most popular Serbian daily news sites, or newspapers sites marked as Croatian... Simply very poor performance. Otherwise, when I use it for German-English, real translation, results are not so bad, actually, they've even improved... But for this total failure in distinguishing Serbian from Croatian - total minus... Don't know if somebody can do anything about that? -- You received this message because you are subscribed to the Google Groups "General" group. To view this discussion on the web visit https://groups.google.com/d/msg/google-translate-general/-/rfCoafTIc8kJ. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/google-translate-general?hl=en.
