Q. I really want to learn Korean and last time I tried google translator I thought it was really good and helpful but I'm not sure if everything you translate is 100% correct.
A. For specific words it's generally accurate, but if you translate an entire sentence, the sentence structure is terrible. So, to answer your question, not really, no.
What does 5la9 mean? I tried google translator and searched it on google but nothing works.?
Q. I tried google translator and a bunch of other translators. NONE WORK WITH NUMBERS IN THEM.
BONUS: If arabs replace characters that we dont have on the english keyboard, then how do they choose the numbers?
BONUS: If arabs replace characters that we dont have on the english keyboard, then how do they choose the numbers?
A. 5 = S
9 = G
9 = G
How does the google language translator work?
Q. The google translator translates sentences from one language to another (though the translation is not always correct). I would like to know how it works. Whether it has a database of all the words in all the supported languages with their corresponding meanings? Or if it uses some other mechanism or perhaps an algorithm for the translation.
A. It's statistically-based machine translation[1]. Read all about that in Wikipedia[2].
My take on the articles is this: There is a special database of documents[2] that are translated into various languages--a really big Rosetta stone. The phrase to be translated is located in a document of the source language then cross-referenced to the various translations in the target language. Of the various possible translations, statistical analysts is used to determine which to use. Grammar and other elements of language are considered in the analysis.
What follows is a quote from the beginning of Wikipedia's description of the basis of statistically-based machine translation. After the quote, it gets very involved in information theory:
"The idea behind statistical machine translation comes from information theory. A document is translated according to the probability distribution p(e | f) that a string e in the target language (for example, English) is the translation of a string f in the source language (for example, French)."
_
My take on the articles is this: There is a special database of documents[2] that are translated into various languages--a really big Rosetta stone. The phrase to be translated is located in a document of the source language then cross-referenced to the various translations in the target language. Of the various possible translations, statistical analysts is used to determine which to use. Grammar and other elements of language are considered in the analysis.
What follows is a quote from the beginning of Wikipedia's description of the basis of statistically-based machine translation. After the quote, it gets very involved in information theory:
"The idea behind statistical machine translation comes from information theory. A document is translated according to the probability distribution p(e | f) that a string e in the target language (for example, English) is the translation of a string f in the source language (for example, French)."
_
Powered by Yahoo! Answers
No comments:
Post a Comment