Views
No views yet
instruction-tuning the corresponding ClueAI/PromptCLUE-base-v1-5 model on the spelling error corpus.ChineseClueAI/PromptCLUE-base-v1-51M UDN news corpusshibing624/CSC spelling error corpus (CN + TC)| Model | Base Model | accuracy | recall | precision | F1 | FPR |
|---|---|---|---|---|---|---|
| GECToR | hfl/chinese-macbert-base | 71.7 | 71.6 | 71.8 | 71.7 | 28.2 |
| GECToR_large | hfl/chinese-macbert-large | 73.7 | 76.5 | 72.5 | 74.4 | 29.1 |
| T5 w/ pretrain | ClueAI/PromptCLUE-base-v1-5 | 79.2 | 69.2 | 85.8 | 76.6 | 11.1 |
| T5 w/o pretrain | ClueAI/PromptCLUE-base-v1-5 | 75.1 | 63.1 | 82.2 | 71.4 | 13.3 |
| PTCSpell | N/A | 79.0 | 89.4 | 83.8 | N/A | |
| MDCSpell | N/A | 77.2 | 81.5 | 79.3 | N/A |
1from transformers import AutoTokenizer, T5ForConditionalGeneration
2tokenizer = AutoTokenizer.from_pretrained("CodeTed/Chinese_Spelling_Correction_T5")
3model = T5ForConditionalGeneration.from_pretrained("CodeTed/Chinese_Spelling_Correction_T5")
4input_text = '糾正句子裡的錯字: 為了降低少子化，政府可以堆動獎勵生育的政策。'
5input_ids = tokenizer(input_text, return_tensors="pt").input_ids
6outputs = model.generate(input_ids, max_length=256)
7edited_text = tokenizer.decode(outputs[0], skip_special_tokens=True)