from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
tokenizer = BertTokenizer.from_pretrained("HillZhang/real_learner_bart_CGEC_exam")
model = BartForConditionalGeneration.from_pretrained("HillZhang/real_learner_bart_CGEC_exam")
encoded_input = tokenizer(["北京是中国的都。", "他说：”我最爱的运动是打蓝球“", "我每天大约喝5次水左右。", "今天，我非常开开心。"], return_tensors="pt", padding=True, truncation=True)
if "token_type_ids" in encoded_input:
    del encoded_input["token_type_ids"]
output = model.generate(**encoded_input)
print(tokenizer.batch_decode(output, skip_special_tokens=True))

@inproceedings{zhang-etal-2023-nasgec,
    title = "{Na}{SGEC}: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts",
    author = "Zhang, Yue  and
      Zhang, Bo  and
      Jiang, Haochen  and
      Li, Zhenghua  and
      Li, Chen  and
      Huang, Fei  and
      Zhang, Min"
    booktitle = "Findings of ACL",
    year = "2023"
    }