Laura Hua's Projects
Data and analysis for the BuzzFeed News article, "Hyperpartisan Facebook Pages Are Publishing False And Misleading Information At An Alarming Rate."
An open-source NLP research library, built on PyTorch.
Example notebooks that show how to apply machine learning, deep learning and reinforcement learning in Amazon SageMaker
🧑🏫 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit), optimizers (adam, radam, adabelief), gans(dcgan, cyclegan, stylegan2), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, etc. 🧠
Generating Training Data Made Easy
AutoX is an efficient automl tool, which is mainly aimed at data mining tasks with tabular data.
Everything about class-imbalanced/long-tail learning: papers, codes, frameworks, and libraries | 有关类别不平衡/长尾学习的一切:论文、代码、框架与库
:octocat: A curated awesome list of lists of interview questions. Feel free to contribute! :mortar_board:
awesome material
Awesome Pretrained Chinese NLP Models,高质量中文预训练模型集合
This repository contains recent research on fake news.
TensorFlow code and pre-trained models for BERT
TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)
超轻量级bert的pytorch版本,大量中文注释,容易修改结构,持续更新
BertViz: Visualize Attention in Transformer Models (BERT, GPT2, BART, etc.)
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
“英特尔创新大师杯”深度学习挑战赛 赛道3:CCKS2021中文NLP地址相关性任务
Pre-Training with Whole Word Masking for Chinese BERT(中文BERT-wwm系列模型)
100+ Chinese Word Vectors 上百种预训练中文词向量
ChineseDiachronicCorpus,中文历时语料库,横跨六十余年,包括腾讯历时新闻2000-2016,人民日报历时语料1946-2003,参考消息历时语料1957-2002。基于历时流通语料库,可用于历时语言变化计算、语言监测、社会文化变迁研究提供基础性的语料支持。
互联网首份程序员考公指南,由3位已经进入体制内的前大厂程序员联合献上。
剑指Offer——名企面试官精讲典型编程题
Compare to The Knowledge: Graph Neural Fake News Detection with External Knowledge (ACL 2021)
covid_fake_news
C++那些事
C++ Primer 5 answers
搞定C++:punch:。C++ Primer 中文版第5版学习仓库,包括笔记和课后练习答案。
我的自学笔记,终身更新。
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被全球175所大学采用教学。