zqqqqq1

GPT2-Chinese

Chinese version of GPT2 training code, using BERT tokenizer.

DDParser

百度开源的依存句法分析系统

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。

the-pile

developer-roadmap

developer-roadmap

NLP_pytorch_project

Embedding, NMT, Text_Classification, Text_Generation, NER etc.

entity-recognition-datasets

A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

awesome-knowledge-graph

整理知识图谱相关学习资料

Top-AI-Conferences-Paper-with-Code

MLNLP: This repository is a collection of AI top conferences papers (e.g. ACL, EMNLP, NAACL, COLING, AAAI, IJCAI, ICLR, NeurIPS, and ICML) with open resource code

awesome

😎 Awesome lists about all kinds of interesting topics

pretrained-models

Open Language Pre-trained Model Zoo

bort

Repository for the paper "Optimal Subarchitecture Extraction for BERT"

multilingual-t5

fairseq

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

pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

Pattern-Exploiting-Training

Pattern-Exploiting Training在中文上的简单实验

Depth-Adaptive-GRN

UER-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

chatbot-list

行业内关于智能客服、聊天机器人的应用和架构、算法分享和介绍

BJTUNLP_Practice2020

This is the second version of the practices for the rookies of BJTUNLPers.

ECommerceCrawlers

实战🐍多种网站、电商数据爬虫🕷。包含🕸：淘宝商品、微信公众号、大众点评、企查查、招聘网站、闲鱼、阿里任务、博客园、微博、百度贴吧、豆瓣电影、包图网、全景网、豆瓣音乐、某省药监局、搜狐新闻、机器学习文本采集、fofa资产采集、汽车之家、国家统计局、百度关键词收录数、蜘蛛泛目录、今日头条、豆瓣影评、携程、小米应用商店、安居客、途家民宿❤️❤️❤️。微信爬虫展示项目:

CLUE

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

Chinese-BERT-wwm

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

expert_readed_books

2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，**类，数学类，人物传记书籍

NLP_ability

总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

nlp-papers-with-arxiv

Statistics and accepted paper list of NLP conferences with arXiv link

fucking-algorithm

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

nlp-tutorial

Natural Language Processing Tutorial for Deep Learning Researchers

leetcode

参考@CyC2018的leetcode题解。Java工程师LeetCode刷题必备。主要根据LeetCode的tag进行模块划分，每部分都选取了比较经典的题目，题目以medium和easy为主，少量hard题目。