ShenDezhou / Chinese-PreTrained-BERT
We released BERT-wwm, a Chinese pre-training model based on Whole Word Masking technology, and models closely related to this technology. 我们发布了基于全词遮罩(Whole Word Masking)技术的中文预训练模型BERT-wwm,以及与此技术密切相关的模型
☆60Updated last year
Alternatives and similar repositories for Chinese-PreTrained-BERT:
Users that are interested in Chinese-PreTrained-BERT are comparing it to the libraries listed below
- NLP句子编码、句子embedding、语义相似度:BERT_avg、BERT_whitening、SBERT、SmiCSE☆175Updated 3 years ago
- experiments of some semantic matching models and comparison of experimental results.☆161Updated last year
- 🌈 NERpy: Implementation of Named Entity Recognition using Python. 命名实体识别工具,支持BertSoftmax、BertSpan等模型,开箱即用。☆115Updated last year
- 基于GlobalPointer的实体/关系/事件抽取☆146Updated 3 years ago
- 一个基于预训练的句向量生成工具☆134Updated last year
- 中文机器阅读理解数据集☆102Updated 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
- 基于pytorch_bert的中文多标签分类☆88Updated 3 years ago
- Some Cool NLP and CV Repositories and Solutions (收集NLP中常见任务的开源解决方案、数据集、工具、学习资料等)☆157Updated 3 years ago
- 基于词汇信息融合的中文NER模型☆164Updated 2 years ago
- 文本相似度,语义向量,文本向量,text-similarity,similarity, sentence-similarity,BERT,SimCSE,BERT-Whitening,Sentence-BERT, PromCSE, SBERT☆73Updated 2 months ago
- GlobalPointer的优化版/NER实体识别☆114Updated 3 years ago
- Knowledge Graph☆170Updated 2 years ago
- pytorch中文语言模型预训练☆389Updated 4 years ago
- 真 · “Deep Learning for Humans”☆141Updated 3 years ago
- 基于pytorch的百度UIE命名实体识别。☆57Updated 2 years ago
- 中文无监督SimCSE Pytorch实现☆133Updated 3 years ago
- ☆135Updated 3 years ago
- 全局指针统一处理嵌套与非嵌套NER☆254Updated 3 years ago
- Bert预训练模型fine-tune计算文本相似度☆100Updated last year
- ☆277Updated 2 years ago
- 超长文本分类(大于1000字);文档级/篇章级文本分类;主要是解决长距离依赖问题☆126Updated 3 years ago
- A PyTorch-based toolkit for natural language processing☆155Updated last year
- 文本相似度(匹配)计算,提供Baseline、训练、推理、指标分析...代码包含TensorFlow/Pytorch双版本☆173Updated 2 years ago
- 本NER项目包含多个中文数据集,模型采用BiLSTM+CRF、BERT+Softmax、BERT+Cascade、BERT+WOL等,最后用TFServing进行模型部署,线上推理和线下推理。☆80Updated 3 years ago
- NLP文本增强的两种方式:同义词替换(利用word2vec词表)和回译☆73Updated 3 years ago
- CoSENT、STS、SentenceBERT☆163Updated last week
- 本人项目进行中搜集的数据集,包含原始数据和经过处理后的数据,项目持续更新。☆112Updated 4 years ago
- 中文数据集下SimCSE+ESimCSE的实现☆191Updated 2 years ago
- A light NER Tool,NER标注工具,基于Vue & FastAPI,带NER数据增强☆64Updated 4 years ago