bojone / CoSENT
比Sentence-BERT更有效的句向量方案
☆367Updated 2 years ago
Alternatives and similar repositories for CoSENT:
Users that are interested in CoSENT are comparing it to the libraries listed below
- SimBERT升级版（SimBERTv2）！☆441Updated 2 years ago
- 中文自然语言推理数据集（A large-scale Chinese Nature language inference and Semantic similarity calculation Dataset）☆426Updated 5 years ago
- 3000000+语义理解与匹配数据集。可用于无监督对比学习、半监督学习等构建中文领域效果最好的预训练模型☆291Updated 2 years ago
- CoSENT、STS、SentenceBERT☆163Updated last week
- CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation☆485Updated 2 years ago
- [SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval☆179Updated 2 years ago
- experiments of some semantic matching models and comparison of experimental results.☆161Updated last year
- Mengzi Pretrained Models☆533Updated 2 years ago
- A framework for cleaning Chinese dialog data☆265Updated 3 years ago
- ☆411Updated 11 months ago
- pCLUE: 1000000+多任务提示学习数据集☆478Updated 2 years ago
- SimCSE在中文上的复现，有监督+无监督☆272Updated 3 years ago
- SimCSE在中文任务上的简单实验☆601Updated last year
- 中文自然语言推理与语义相似度数据集☆345Updated 3 years ago
- FewCLUE 小样本学习测评基准，中文版☆503Updated 2 years ago
- 中文生成式预训练模型☆559Updated 2 years ago
- 一个基于预训练的句向量生成工具☆134Updated last year
- Modify Chinese text, modified on LaserTagger Model. 文本复述，基于lasertagger做中文文本数据增强。☆317Updated last year
- ☆265Updated 6 months ago
- 简单的向量白化改善句向量质量☆483Updated 3 years ago
- RoFormer升级版☆152Updated 2 years ago
- Collections of resources from Joint Laboratory of HIT and iFLYTEK Research (HFL)☆368Updated last year
- 全局指针统一处理嵌套与非嵌套NER☆254Updated 3 years ago
- text embedding☆144Updated last year
- Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021☆234Updated 2 years ago
- 语言模型中文认知能力分析☆236Updated last year
- 中文图书语料MD5链接☆213Updated last year
- ☆277Updated 2 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
- 中文NLP数据集☆153Updated 5 years ago