hgliyuhao / cluster
Clustering text with Bert
☆56Updated 4 years ago
Alternatives and similar repositories for cluster:
Users that are interested in cluster are comparing it to the libraries listed below
- 中文无监督SimCSE Pytorch实现☆133Updated 3 years ago
- Use deep models including BiLSTM, ABCNN, ESIM, RE2, BERT, etc. and evaluate on 5 Chinese NLP datasets: LCQMC, BQ Corpus, ChineseSTS, OCN…☆76Updated 2 years ago
- pytorch implementation of multi-label text classification, includes kinds of models and pretrained. Especially for Chinese preprocessing.☆75Updated 5 years ago
- NLP句子编码、句子embedding、语义相似度:BERT_avg、BERT_whitening、SBERT、SmiCSE☆176Updated 3 years ago
- NER任务SOTA模型BERT_MRC☆60Updated last year
- ☆61Updated 4 years ago
- bert pytorch模型微调用于的多标签文本分类☆132Updated 5 years ago
- 微调预训练语言模型,解决多标签分类任务(可加载BERT、Roberta、Bert-wwm以及albert等知名开源tf格式的模型)☆140Updated 4 years ago
- experiments of some semantic matching models and comparison of experimental results.☆160Updated last year
- multi-label,classifier,text classification,多标签文本分类,文本分类,BERT,ALBERT,multi-label-classification,seq2seq,attention,beam search☆32Updated 2 years ago
- 文本分类baseline:BERT、半监督学习UDA、对抗学习、数据增强☆101Updated 3 years ago
- Pytorch进行长文本分类。这里用到的网络有:FastText、TextCNN、TextRNN、TextRCNN、Transformer☆46Updated 4 years ago
- ☆91Updated 4 years ago
- ☆88Updated 3 years ago
- 中文数据集下SimCSE+ESimCSE的实现☆191Updated 2 years ago
- Pattern-Exploiting Training在中文上的简单实验☆170Updated 4 years ago
- lic2020关系抽取比赛,使用Pytorch实现苏神的模型。☆101Updated 4 years ago
- 本项目采用Keras和Keras-bert实现文本多标签分类任务,对BERT进行微调。☆66Updated 3 years ago
- ☆278Updated 2 years ago
- code for ACL2020:《FLAT: Chinese NER Using Flat-Lattice Transformer》 我注释&修改&添加了部分源码,使得大家更容易复现这个代码。☆56Updated 4 years ago
- Bert预训练模型fine-tune计算文本相似度☆100Updated last year
- 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☆128Updated 3 years ago
- 本项目是NLP领域一些任务的基准模型实现,包括文本分类、命名实体识别、实体关系抽取、NL2SQL、CKBQA以及BERT的各种下游任务应用。☆47Updated 4 years ago
- 基于pytorch + bert的多标签文本分类(multi label text classification)☆102Updated last year
- 2020 CCF大数据与计算智能大赛-非结构化商业文本信息中隐私信息识别-第7名方案☆73Updated 4 years ago
- 基于词汇信息融合的中文NER模型☆165Updated 2 years ago
- SEBERTNets:一种面向金融领域的事件主体抽取方法☆193Updated 2 years ago
- TPlinker for NER 中文/英文命名实体识别☆123Updated 3 years ago
- 基于prompt的中文文本分类。☆54Updated last year
- 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