LowinLi / chinese-bigbird
中文bigbird预训练模型
☆91Updated 2 years ago
Alternatives and similar repositories for chinese-bigbird:
Users that are interested in chinese-bigbird are comparing it to the libraries listed below
- chinese version of longformer☆112Updated 4 years ago
- 句子匹配模型,包括无监督的SimCSE、ESimCSE、PromptBERT,和有监督的SBERT、CoSENT。☆98Updated 2 years ago
- ☆88Updated 3 years ago
- 中文无监督SimCSE Pytorch实现☆133Updated 3 years ago
- P-tuning方法在中文上的简单实验☆139Updated 3 years ago
- 基于“Seq2Seq+前缀树”的知识图谱问答☆70Updated 3 years ago
- 收集了目前为止中文领域的MRC抽取式数据集☆119Updated 8 months ago
- CTC2021-中文文本纠错大赛的SOTA方案及在线演示☆72Updated last year
- OCNLI: 中文原版自然语言推理任务☆153Updated 3 years ago
- SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec,which can be used for…☆62Updated 3 years ago
- 中文机器阅读理解数据集☆102Updated 3 years ago
- CCL 2022 汉语学习者文本纠错评测☆138Updated 2 years ago
- 基于SpanBert的中文指代消解,pytorch实现☆97Updated 2 years ago
- pytorch Efficient GlobalPointer☆53Updated 2 years ago
- Pattern-Exploiting Training在中文上的简单实验☆170Updated 4 years ago
- ☆57Updated 2 years ago
- This is the official code for paper titled "Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models".☆67Updated 3 years ago
- ☆127Updated 2 years ago
- 中文版unilm预训练模型☆83Updated 4 years ago
- RoFormer升级版☆152Updated 2 years ago
- Data Augmentation with a Generation Approach for Low-resource Tagging Tasks☆80Updated 4 years ago
- R-Drop方法在中文任务上的简单实验☆90Updated 3 years ago
- 百度2021年语言与智能技术竞赛机器阅读理解torch版baseline☆53Updated 3 years ago
- The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".☆114Updated last year
- code for ACL2021 paper "Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction"☆99Updated 3 years ago
- CLUEWSC2020: WSC Winograd模式挑战中文版,中文指代消解任务☆73Updated 4 years ago
- 对话改写介绍文章☆95Updated last year
- 中文数据集下SimCSE+ESimCSE的实现☆191Updated 2 years ago
- 继续预训练中文bert☆30Updated 3 years ago
- ☆32Updated 3 years ago