Re: Biggest Google Translate Fail
Posted: Thu Oct 31, 2019 7:05 am
I actually did a speech about Google translate and its vagaries in Berlin in 2016, and afterwards I wrote a thread named "A couple of suggestions to Google Translate from a heavy user" with some examples I had found during my preparations. The purpose was not to mock GT, but to point out some areas where it could be improved without compromising the automatic exploratory model which is the basis of its construction - mostly simple things like putting at least one big dictionary per language into the beast so that it stops doing idiotic translations because it meets unknown words. As the title indicates I'm a heavy user, but only one way: I don't trust it enough to use it to produce texts in my target languages, but I do use it to make bilingual texts for study. This allows me to work on texts that normally would be too difficult at my current level in the different target languages, and then it is less important whether it makes silly errors as long as I can spot them - and you can spot most of GT's errors because they are so obvious.
I'll quote one example from that thread. The original text comes from the homepage of Reykjavík Park and Zoo:
Sauðburður er hafinn. (...) Ærin Surtla bar tveimur hrútlömbum og ærin Melkorka bar þremur gimbrum snemma morguns þann 4.maí.
GT: Lambing is underway. (...). Aerials acid bar two ram lambs, and there are clear Melkorka bar three ewe early on 4.maí.
correct: Lambing is underway. (...) The ewe Surtla bore two ram lambs and the ewe Melkorka bore three ewe lambs in the morning on the 4. of May.
"Aerials acid bar two ram lambs" should awake the suspicion of any language user - and it exemplifies the idea that most errors of Google are relatively innocuous precisely because they are too gross to go unnoticed. In fact "ærin" means "the (mother)sheep" - it's an irregular substantive. Surtla is a proper name, as evidenced by the capital letter - it is related to the name of Surt, the god of fire in the old Norse Mythology, not to súr (sour as in acid) - and as a proper name it should not be translated. And then "bar". In the original it is a form of the irregular verb "bera" - neither a place to have a drink nor an oblong object of some kind.
I'll quote one example from that thread. The original text comes from the homepage of Reykjavík Park and Zoo:
Sauðburður er hafinn. (...) Ærin Surtla bar tveimur hrútlömbum og ærin Melkorka bar þremur gimbrum snemma morguns þann 4.maí.
GT: Lambing is underway. (...). Aerials acid bar two ram lambs, and there are clear Melkorka bar three ewe early on 4.maí.
correct: Lambing is underway. (...) The ewe Surtla bore two ram lambs and the ewe Melkorka bore three ewe lambs in the morning on the 4. of May.
"Aerials acid bar two ram lambs" should awake the suspicion of any language user - and it exemplifies the idea that most errors of Google are relatively innocuous precisely because they are too gross to go unnoticed. In fact "ærin" means "the (mother)sheep" - it's an irregular substantive. Surtla is a proper name, as evidenced by the capital letter - it is related to the name of Surt, the god of fire in the old Norse Mythology, not to súr (sour as in acid) - and as a proper name it should not be translated. And then "bar". In the original it is a form of the irregular verb "bera" - neither a place to have a drink nor an oblong object of some kind.