As far as I know, DeepL is allowed to (and will prioritize) naturally-sounding sentences so it feeds in the extra context it received during ML model training. There are some cases where the answer is extremely specific (f.e. a name of a particular institution) which shows that the data set was oddly unbalanced.
2 Likes
I havenât think of this much before, but there is a possibility of using DeepL to translate to Japanese (with a grain of salt, nonetheless).
I canât yet find a fitting vocabulary for vocabulary hunting, though.
1 Like
Seriously, Google, whatâs wrong with you?
As for Deepl, it was in a rather negative mood lately:
Removing the extra sentences wasnât especially helpful:
4 Likes
You and me both Google. Iâd say someone needs to whip Google into shape but from the sounds of it⊠it might enjoy it.
1 Like
This topic was automatically closed 365 days after the last reply. New replies are no longer allowed.