News for hackers. Stuff that matters.

A comment on The most frequent 777 characters give 90% coverage of Kanji in the wild. Parent comment

Re:The most frequent 777 characters give 90% coverage of Kan... by derefr on Saturday August 17, 2019 @11:25AM (#20724483)
Do kanji handwriting-recognition models even “know” (i.e. are trained on) all in-use kanji, or do they just not bother with some of the rarest ones because their presence in the dataset would decrease the likelihood of correctly matching more-common characters, which it’s overwhelmingly-likely are what you’re writing?
[ Parent | on HN ]
Re:The most frequent 777 characters give 90% coverage of Kan... by esrauch on Monday August 19, 2019 @09:31AM (#20737554)
Presumably it's the same as words in English, where you'd never make a word suggestion model that just blindly considers all possible words. You swipe jow or gow and it will change it to "how" despite the other two existing in arguably correct English in some very obscure case.
[ Parent | on HN ]