jiangtaojy / mlm_bert_traning
基于mlm方式的带有纠错功能的拼音转汉字bert预训练模型,pinyin correcter,基于pytorch框架实现
☆45Updated 4 years ago
Alternatives and similar repositories for mlm_bert_traning:
Users that are interested in mlm_bert_traning are comparing it to the libraries listed below
- ☆127Updated 2 years ago
- Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021☆234Updated 2 years ago
- 中文版unilm预训练模型☆83Updated 4 years ago
- 中国中文信息学会社会媒体处理专业委员会举办的2019届中文人机对话之自然语言理解竞赛☆74Updated 4 years ago
- ☆91Updated 4 years ago
- This is the official code for paper titled "Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models".☆68Updated 3 years ago
- SIGHAN中文纠错数据集及转换后格式☆62Updated 5 years ago
- 对话改写介绍文章☆95Updated last year
- ☆102Updated 4 years ago
- bert语言模型校验句子的通顺性☆15Updated 4 years ago
- This repo contains some experiments of text matching on Chinese dataset LCQMC☆27Updated 5 years ago
- 🙈 An unofficial implementation of SoftMaskedBert based on huggingface/transformers.☆95Updated 3 years ago
- DistilBERT for Chinese 海量中文预训练蒸馏bert模型☆91Updated 5 years ago
- ☆88Updated 3 years ago
- 基于BERT的无监督分词和句法分析☆110Updated 4 years ago
- 中文NLP数据集☆153Updated 5 years ago
- ☆89Updated 4 years ago
- A Multi-modal Model Chinese Spell Checker Released on ACL2021.☆155Updated last year
- SpellGCN☆251Updated 4 years ago
- Python toolkit for Chinese Language Understanding(CLUE) Evaluation benchmark☆129Updated last year
- lasertagger-chinese;lasertagger中文学习案例,案例数据,注释,shell运行☆75Updated 2 years ago
- Bert finetune for CMRC2018, CJRC, DRCD, CHID, C3☆182Updated 4 years ago
- 基于bert进行中文文本纠错☆232Updated last year
- Pytorch-BERT-CRF-NER;Chinese-Named-Entity-Recognition☆46Updated 3 years ago
- CGED & CSC☆22Updated 5 years ago
- chinese and english corpus process script, python, c++, java☆198Updated 6 years ago
- 李傲龍的博客☆81Updated 8 months ago
- 转换 https://github.com/brightmart/albert_zh 到google格式☆62Updated 4 years ago
- ☆51Updated 4 years ago
- CCL 2022 汉语学习者文本纠错评测☆138Updated 2 years ago