ZephyrChenzf / text-classification-pytorchLinks
使用pytorch和京东某商品评价数据集,采用不同模型对文本进行分类
☆25Updated 7 years ago
Alternatives and similar repositories for text-classification-pytorch
Users that are interested in text-classification-pytorch are comparing it to the libraries listed below
Sorting:
- 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
- Bert中文文本分类☆40Updated 6 years ago
- 面向金融领域的事件主体抽取(ccks2019),一个baseline☆119Updated 6 years ago
- 汽车主题情感分析大赛冠军☆27Updated 6 years ago
- Byte Cup 2018国际机器学习竞赛 23 名(水滴队)代码☆46Updated 6 years ago
- 主要是实现nlp常用网络以及结果比较,各模型的优劣势,如:FastText,TextCNN,TextRNN,TextRCNN,BiLSTM,Seq2seq,BERT,Transformer,ELMo以及Attention机制等等。☆45Updated 6 years ago
- 参考NER,基于BERT的电商评论观点挖掘和情感分析☆41Updated 5 years ago
- 在bert模型的pre_training基础上进行text_cnn文本分类☆78Updated 5 years ago
- 两层attention 的lstm评论情感分析☆22Updated 7 years ago
- Our experience & lesson & code☆48Updated 8 years ago
- 基于ELMo, tensorflow的中文命名实体标注 Chinese Named Entity Recognition Based on ELMo☆21Updated 5 years ago
- 关键词抽取,神策杯2018高校算法大师赛比赛,solo 排名3/591☆65Updated 6 years ago
- 搜狐校园算法大赛baseline☆66Updated 6 years ago
- 蚂蚁金服比赛 15th/2632☆47Updated 6 years ago
- NLP的数据增强Demo☆47Updated 5 years ago
- use ELMo in chinese environment☆104Updated 6 years ago
- seq2seq+attention model for Chinese textsum☆41Updated 7 years ago
- Bert-classification and bert-dssm implementation with keras.☆93Updated 4 years ago
- 之江-电商评论观点挖掘的比赛,基于pytorch-transformers版本,暂时只实现了BERT做aspect+opinion+属性分类+情感极性的联合标注,还未加上CRF。☆32Updated 5 years ago
- BiLSTM+CRF by Pytorch and classic CRF by pysuite 基于双向循环神经网络和CRF特征模板的信息抽取☆17Updated 6 years ago
- 复盘所有NLP比赛的TOP方案,只关注NLP比赛,持续更新中!☆47Updated 5 years ago
- paper reading☆20Updated 6 years ago
- 使用分层注意力机制 HAN + 多任务学习 解决 AI Challenger 细粒度用户评论情感分析 。https://challenger.ai/competition/fsauor2018☆58Updated 6 years ago
- ☆31Updated 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
- Paper notes: Linguistically Regularized LSTM for Sentiment Classification☆7Updated 6 years ago
- CSDN博客的关键词提取算法,融合TF,IDF,词性,位置等多特征。该项目用于参加2017 SMP用户画像测评,排名第四,在验证集中精度为59.9%,在最终集中精度为58.7%。启发式的方法,通用性强。☆30Updated 7 years ago
- CHIP2018评测任务2,平安医疗科技智能患者健康咨询问句匹配大赛baseline,BiLSTM+特征工程计算相似性,10折交叉验证平均投票做bagging,F1值0.83左右,rank16。☆19Updated 6 years ago
- siamese dssm sentence_similarity sentece_similarity_rank tensorflow☆60Updated 6 years ago
- textcnn多标签文本分类☆37Updated 6 years ago