language: - lzh tags: - classical chinese - literary chinese - ancient chinese - masked-lm license: apache-2.0 pipeline_tag: fill-mask mask_token: '[MASK]' widget: - text: 孟子[MASK]梁惠王
This is a RoBERTa model pre-trained on Classical Chinese texts, derived from GuwenBERT-large. Character-embeddings are enhanced into traditional/simplified characters. You can fine-tune
roberta-classical-chinese-large-char for downstream tasks, such as sentence-segmentation, POS-tagging, dependency-parsing, and so on.
from transformers import AutoTokenizer,AutoModelForMaskedLM tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char") model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char")
SuPar-Kanbun: Tokenizer POS-tagger and Dependency-parser for Classical Chinese