It might be a bug, I cannot reproduce it in my version. You should contact the support team using https://www.wolfram.com/support/contact/email/?topic=feedback

All methods in the page I have tried. But none of them can work.

There was a bug found in the pre-processing BERT when the front-end language is not English (for instance when it is Chinese).

We will update BERT to fix it. (and people who already downloaded the model will have to re-download it after having called ResourceRemove@ResourceObject["BERT Trained on BookCorpus and English Wikipedia Data"])

In the meantime the workaround for this bug is:

net = NetModel[{"BERT Trained on BookCorpus and English Wikipedia Data", "InputType" -> "ListOfStrings"}]

net2 = NetReplacePart[net, {"Input", "Function"} ->
   ReplaceAll[NetExtract[net, {"Input", "Function"}],
    RemoveDiacritics -> Function @ RemoveDiacritics[#, Language -> "English"]]]

then use net2 in place of net.