yanqiuxia / BERT-PreTrain
不用tensorflow estimator,分别采用字mask和wwm mask在中文领域内finetune bert模型
☆23Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for BERT-PreTrain
- This repo contains some experiments of text matching on Chinese dataset LCQMC☆27Updated 4 years ago
- 达观算法比赛ner任务,从重新训练bert,到finetune预测。☆76Updated 2 years ago
- 天池-新冠疫情相似句对判定大赛 Rank8☆52Updated 4 years ago
- this is roberta wwm base distilled model which was distilled from roberta wwm by roberta wwm large☆65Updated 4 years ago
- CNN、BiLSTM、Bert(3layers)对Bert(12layers)模型的蒸馏的keras实现☆27Updated 4 years ago
- CGED & CSC☆22Updated 4 years ago
- 迭代膨胀卷积命名实体抽取☆45Updated 5 years ago
- 2019百度语言与智能技术竞赛信息抽取赛代5名代码☆69Updated 5 years ago
- tensorflow version of bert-of-theseus☆63Updated 3 years ago
- 2020语言与智能技术竞赛:关系抽取任务(https://aistudio.baidu.com/aistudio/competition/detail/31?lang=zh_CN)☆25Updated 4 years ago
- 开天-新词,中文新词发现工具,Chinese New Word Discovery Tool☆20Updated 4 years ago
- using lear to do ner extraction☆29Updated 2 years ago
- ☆13Updated 4 years ago
- multi-label,classifier,text classification,多标签文本分类,文本分类,BERT,ALBERT,multi-label-classification☆27Updated 3 years ago
- lic2020关系抽取比赛,使用Pytorch实现苏神的模型。☆102Updated 4 years ago
- NLP中文预训练模型泛化能力挑战赛☆42Updated 3 years ago
- chinese pretrain unilm☆28Updated 4 years ago
- TensorFlow code and pre-trained models for BERT☆9Updated 3 years ago
- ☆92Updated 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
- 关键词抽取项目☆24Updated 4 years ago
- Label Mask for Multi-label Classification☆55Updated 3 years ago
- 天池中药说明书实体识别挑战冠军方案;中文命名实体识别;NER; BERT-CRF & BERT-SPAN & BERT-MRC;Pytorch☆23Updated 3 years ago
- Just Code ! 针对面试训练算法题, 目前包括字节跳动面试题、 LeetCode 和剑指 offer ,持续扩容中☆18Updated 4 years ago
- NLP的数据增强Demo☆47Updated 4 years ago
- BDCI2019-互联网金融新实体发现-第7名(本可top3)☆18Updated 4 years ago
- 2019之江杯人工智能大赛电商评论观点挖掘赛道top3☆45Updated 5 years ago
- 转换 https://github.com/brightmart/albert_zh 到google格式☆62Updated 4 years ago
- 基于tensorflow的bilstm+crf的命名实体识别☆12Updated 4 years ago
- NLP实验:新词挖掘+预训练模型继续Pre-training☆47Updated last year