chenywang / hierarchical_attention_modelLinks
基于attention的文本分类,并且提供了可视化界面
☆9Updated 6 years ago
Alternatives and similar repositories for hierarchical_attention_model
Users that are interested in hierarchical_attention_model are comparing it to the libraries listed below
Sorting:
- paper reading☆20Updated 6 years ago
- notes and codes about NLP☆24Updated 6 years ago
- 2019年4月8日,第三届搜狐校园内容识别算法大赛。☆25Updated 6 years ago
- CCKS 2018 开放领域的中文问答任务 1st 解决方案☆110Updated 6 years ago
- ☆31Updated 6 years ago
- 蚂蚁金服比 赛 15th/2632☆47Updated 6 years ago
- 基于BiLSTM和Self-Attention的文本分类、表示学习网络☆29Updated 6 years ago
- code for Baidu machine reading comprehension competition☆10Updated 6 years ago
- 基于句法分析的命名实体关系抽取程序☆65Updated 9 years ago
- 2018年机器阅读理解技术竞赛总结,国内外1000多支队伍中BLEU-4评分排名第6, ROUGE-L评分排名第14。(未ensemble,未嵌入训练好的词向量,无dropout)☆30Updated 6 years ago
- Relation Extraction 中文关系提取☆73Updated 6 years ago
- 主要和大家分享今年2019年的ACL paper☆32Updated 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 6 years ago
- Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms☆95Updated 6 years ago
- ene to end neural coreference resolution(forked from https://github.com/kentonl/e2e-coref and make some little change)☆20Updated 6 years ago
- 面向金融领域的事件主体抽取(ccks2019),一个baseline☆119Updated 6 years ago
- 2019搜狐校园算法大赛。决赛解决方案ppt、实体lgb单模代码☆70Updated 6 years ago
- PyTorch Bert Text Classification☆31Updated 6 years ago
- 中文预训练模型生成字向量学习,测试BERT,ELMO的中文效果☆99Updated 5 years ago
- baseline for ccks2019-ipre☆48Updated 5 years ago
- 基于条件随机场的医疗电子病例的命名实体识别☆113Updated 7 years ago
- 汽车主题情感分析大赛冠军☆27Updated 6 years ago
- pytorch用Textcnn-bilstm-crf模型实现命名实体识别☆41Updated 7 years ago
- 关系抽取个人实战总结以及开源工具包使用☆56Updated 6 years ago
- Joint Extraction of Entity Mentions and Relations without Dependency Trees☆18Updated 7 years ago
- 2019达观杯 第六名代码☆43Updated 2 years ago
- 关于文本分类的许多方法,主要涉及到TextCNN,TextRNN, LEAM, Transformer,Attention, fasttext, HAN等☆75Updated 6 years ago
- ☆23Updated 6 years ago
- Bert中文文本分类☆40Updated 6 years ago
- A Chinese word segment model based on BERT, F1-Score 97%☆93Updated 6 years ago