ZeweiChu / nmt-seq2seq
seq2seq model written in Pytorch
☆93Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for nmt-seq2seq
- 基于BERT的中文序列标注☆142Updated 6 years ago
- 2018-JDDC大赛第4名的解决方案☆238Updated 6 years ago
- BDCI2017-让AI当法官,决赛第四(4/415)https://www.datafountain.cn/competitions/277/details☆118Updated 6 years ago
- seq2seq+attention model for Chinese textsum☆42Updated 6 years ago
- CCL2018客服领域用户意图分类冠军1st方案☆148Updated 2 years ago
- 搜狐算法大赛:主要实体词情绪识别 baseline☆105Updated 5 years ago
- QANet+DuReader中文机器阅读理解☆223Updated 6 years ago
- A pytorch implementation of Attention is all you need☆90Updated 5 years ago
- 基于capsule的观点型阅读理解模型☆89Updated 5 years ago
- 2018达观杯文本智能处理挑战赛 Top10解决方案(10/3830)☆216Updated 6 years ago
- XLNet: Generalized Autoregressive Pretraining for Language Understanding 论文的中文翻译 Paper Chinese Translation!☆50Updated 5 years ago
- 第三届魔镜杯 智能客服问题相似性算法设计 第12名解决方案☆149Updated 5 years ago
- 面向金融领域的事件主体抽取(ccks2019),一个baseline☆118Updated 5 years ago
- An Implementation of 'Attention is all you need' with Chinese Corpus☆130Updated 6 months ago
- Code for Fine-grained Sentiment Analysis of User Reviews of AI Challenger 2018☆169Updated 5 years ago
- pytorch learning eamples☆25Updated 6 years ago
- keras sparse implement of margin-softmax☆100Updated 6 years ago
- Deep contextualized word representations for Chinese☆152Updated 5 years ago
- keras example of seq2seq, auto title☆332Updated 4 years ago
- 知乎看山杯 第二名 解决方案☆242Updated 5 years ago
- Convolutional neural network and word embeddings for Chinese word segmentation☆142Updated 2 years ago
- 2019年百度的实体链指比赛(ccks2019),一个baseline☆114Updated 5 years ago
- 基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs☆143Updated 6 years ago
- 中文预训练XLNet模型: Pre-Trained Chinese XLNet_Large☆230Updated 5 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☆97Updated 4 years ago
- TestB榜第10的方案,bleu32.1☆63Updated 4 years ago
- AI Challenger 2018 观点型问题阅读理解 复赛第8名 解决方案 (8th place of AI Challenger 2018 MRC)☆91Updated 5 years ago
- A Chinese word segment model based on BERT, F1-Score 97%☆90Updated 5 years ago