You are reading a single comment by @houshou_m and its replies.
Click here to read the full conversation.
-
你 的 验证码 是 698449，此 验证码 用 于 登录 知乎 或 重置 密码。10 分钟 内 有效
so in this example,
你, 1
验证码, 3
登录, 2i 'll say in the author 's orginal line, he/she have already considered that others will understand his/her line without spaces 【知乎】你的验证码是 698449，此验证码用于登录知乎或重置密码。10 分钟内有效。
i just afraid if you rely on the android phone or bangle to choose the length of the phrases, it may hurt, because sometimes the phrases in the dictionary are overlapped, pre-GPT4 AI dont have the ability to do so. And even GPT4 is not good in chinese too. (but chinese made their own AI which process chinese better).
ccchan
@houshou_m
The typical Mandarin written word consists of either one or two graphs, with two being more common. For reference, the notification text can be broken down into the following "dictionary words":
你 的 验证码 是 698449，此 验证码 用 于 登录 知乎 或 重置 密码。10 分钟 内 有效。
The simplest solution might be to simply preserve groupings of two. Unlike the Latin script, Chinese characters are all meant to be written such that they take up the same amount of space (like monospace fonts do), so perhaps that wouldn't be too difficult a task?