Apparently deepl thinks that the discovery of America cannot have taken place in 1492 and autocorrects the year to 1942!
Is that the director of Harry Potter?
Yeah. Also, I’m increasingly noticing that when translating larger blocks of text, Deepl will occasionally replace a sentence’s translation with the translation of the sentence next to it, and it’ll keep using that translation even when I’ve deleted the adjacent sentence.
Deepl, only one of those bullet points actually reads “Do not use if you have scars, rashes, or other skin problems.” And if I delete that bullet point from the original text, it simply removes one of the “Do not use…” lines from the translation.
It’s doing me a concern.
Off topic. I’ve never used deepl, how does it compare to Google’s translator?
EDIT: I’ve noticed now that it doesn’t allow translation from English to Japanese, only the contrary, so it can’t fully replace Google as of now
Toss all the numbers in a bag, shake it up, and draw them out at random.
It’s several orders of magnitude better, with the biggest caveat being that it tends to favour a natural-sounding translation over an accurate one. So, sometimes it… guesses.
Ohhh, I noticed that too! So I’m not insane!
The trick is that you need to set the “from” language to English first. Then Japanese appears in the “to” language list.
This could be that they trained the network on texts that contained mistakes like that, and so now the network has learned the mistake!
Thanks, that’s very useful to know.
1942 was the battle of Midway so maybe it just parsed a lot of text containing that year.
its not a translater, it’s a fancy statistical language model
Yeah but that’s pretty much all of us as well. lol
lets not repeat the AGI debate we had before (fun as it was)
I like that it goes for a more natural-sounding translation over a literal one, but Google has the romaji along the bottom which is really nice if I am copy/pasting a chunk of text I can’t read. It’s not perfect, but it is nice.
Perhaps deepl can’t decide between Japanese and Chinese - so it must be German
However it works here. Does deepl know that I am using it mostly for Japanese?
This is the first time Ive ever had issue with deepl auto detecting Japanese, so it surprised me.
I think that is related to kanji-only expressions, where there may be ambiguities with Chinese. I am using google translate as “background translator” with bookwalker, and I have often been told “translated from Chinese” when I mark only kanji. It doesn’t give pronunciation then, but gives the correct translation. When I select more than just kanji, it recognizes Japanese and all is well.
河豚 was a word in an ancient Germanic language, which later split into several new languages, including German and English. The word 河豚 managed to remain unchanged in both of them