This can simulate a little more of the influence of context on each word choice. A variation called a hidden Markov model introduces "states", where each state has its own set of probabilities for "emitting" words as well as a set of "transition" probabilities for what will be the next state. If you use a window of more words, say five, the resulting gibberish will look more likely to have been written by a schizophrenic than by an aphasic. If you generate new text according to these probabilities, you'll get random but just slightly coherent gibberish: TWO OR BUTANE GAS AND OF THE SAME. You could calculate these word-to-next-word probabilities from their frequencies in real text. If you just said "or", there is a certain probability that your next word will be "butane". For example, if the last word you said was "two", there is a certain probability that your next word will be "or". A simple way is to say that the probability of each word is determined by the previous word spoken.
#Google stacks how to
The only question now is how to calculate the probabilities. Ignore all the complexity, structure, and meaning of language and pretend that people speak just by randomly choosing one word after another. It works by correlating sequences of up to five consecutive words found in texts from both languages. It has no model of grammar, syntax, or meaning. Google Translate is completely statistical. But I just did a little, er, googling, and this seems to be passably well corroborated by other sources. It might be out of date and I might be remembering it wrong. in natural-language processing and now works at Google told me the following.
The question whether Google Translate can be trusted for anything at all regarding Latin.Ī classmate of mine who got his Ph.D. Original → Google translation (better translation if Google fails)įor translating individual words it's better to look at any online Latin dictionary.īut my question is not whether there are better tools than Google Translate. It would be good to know if there is something it is useful and reliable for, even if the scope is very limited. The tool might work better for translating individual words 2 or with some language other than English.Īnd perhaps it does translate simple SVO clauses consistently well from English to Latin - I did not do an extensive test, and I have no prior experience.ĭoes someone have more experience with Google Translate? Google does offer alternatives, and some of them greatly improve the last sentence, but someone with no knowledge in Latin will not be able to pick the right ones. It seems that translation from Latin to English is very difficult even with simple structures.Įnglish to Latin is much better, but it fails for the slightly more complicated sentence. (Whether or not the content makes sense should not affect translation in simple cases like this, but it might be that Google Translate is not wired that way.)
These might not be the perfect example sentences, but they demonstrate some basic syntax. (Puer et canis una ambulant quia non pluit.) → Puer et canis ambulare quia non pluet simul. The boy and the dog walk together because it does not rain.I tried it for simple phrases to and from English. Is there some kind of translation task involving Latin that Google Translate is relatively reliable for? However, the translations do make some amount of sense. Google Translate is notoriously unreliable for Latin.
0 kommentar(er)
