Makaixin

caffeine. A high performance caching library for Java

ccks_ner. ccks2020 NER competitions

ape210k. This is the repository of the Ape210K dataset and baseline models.

WoBERT. 以词为基本单位的中文BERT

Chinese-BERT-wwm. Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

roberta_zh. RoBERTa中文预训练模型: RoBERTa for Chinese

Flat-Lattice-Transformer. code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer

Tencent2020_Rank1st. The code for 2020 Tencent College Algorithm Contest, and the online result ranks 1st.

Pretraining-Yourself-Bert-From-Scratch. 从头训练MASK BERT

Top-AI-Conferences-Paper-with-Code. MLNLP：本仓库整理人工智能会议（如 ACL、EMNLP、NAACL、COLING、AAAI、IJCAI、ICLR、NeurIPS、ICML 等）中开源代码的论文。

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

rank6. 天池-新冠疫情相似句对判定大赛 大白_Rank6

epidemic-sentence-pair. 天池 疫情相似句对判定大赛 线上第一名方案

nlpcda. 一键中文数据增强包 ； NLP数据增强、bert数据增强、EDA：pip install nlpcda

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

kg-2019. 2019年百度的三元组抽取比赛，“科学空间队”源码

epidemicTextMatch. 天池大赛疫情文本挑战赛线上第三名方案分享

Chinese-ELECTRA. Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

BDCI2019-SENTIMENT-CLASSIFICATION. CCF BDCI 2019 互联网新闻情感分析 复赛top1解决方案

ccf_financial_negative. CCF BDCI 金融信息负面及主体判定 冠军代码

2019-CCF-BDCI-NLP. 2019 CCF BDCI 技术需求与技术成果项目之间关联度计算模型第二名、2019 CCF BDCI 互联网金融新实体发现第四名、2019 CCF BDCI 金融信息负面及主体判定第五名

CCF-BDCI-ABSA. CCF BDCI 金融信息负面及主体判定第三名方案

2019-CCF-BDCI-Car_sales. 2019年CCF大数据与计算智能大赛乘用车细分市场销量预测冠军解决方案