glenn1q84 Goto Github PK

glenn1q84.github.io

personal page

hanlp

中文分词 词性标注 命名实体识别 依存句法分析 语义依存分析 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

hello-world

print hello world

icd-10-cn

ICD-10 Chinese Verion

ijson

Iterative JSON parser with Pythonic interfaces

introduction-nlp

HanLP作者的新书《自然语言处理入门》详细笔记！业界良心之作，书中不是枯燥无味的公式罗列，而是用白话阐述的通俗易懂的算法模型。从基本概念出发，逐步介绍中文分词、词性标注、命名实体识别、信息抽取、文本聚类、文本分类、句法分析这几个热门问题的算法原理与工程实现。

jieba

结巴中文分词

keyword_extraction

利用Python实现中文文本关键词抽取，分别采用TF-IDF、TextRank、Word2Vec词聚类三种方法。

knowledgegraphcourse

东南大学《知识图谱》研究生课程

latte

Wow, A cup of Latte！ A zhihu crawler~ 灵活[简易]知乎爬虫

listen1_chrome_extension

one for all free music in china (chrome extension, also works for firefox)

lstm-char-cnn

LSTM language model with CNN over characters

ltp

Language Technology Platform

machine-learning-code-writing

Mathematical derivation and pure Python code implementation of machine learning algorithms.

meddg

a large-scale high-quality medical dialogue dataset

medical-dialogue-system

miningzhidaoqacorpus

ZhiDaoChatCorpus, zhidao QA pairs crawled from Baidu zhidao which contains more than 5,800,000 question and 9,830,000 answers with certain tags。百度知道问答语料库，包括超过580万的问题，938万的答案，5800个分类标签。基于该问答语料库，可支持多种应用，如闲聊问答，逻辑挖掘。

ml-note

:orange_book:慢慢整理所学的机器学习算法，并根据自己所理解的样子叙述出来。(注重数学推导)

ml-visuals

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

network-modules

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

newspaper

News, full-text, and article metadata extraction in Python 3. Advanced docs:

ngram2vec

Four word embedding models implemented in Python. Supporting arbitrary context features

nlp-paradigm-shift

online_pca

courses: A Brief Survey of Approaches for Unconstrained Optimization Problems

opencc

Conversion between Traditional and Simplified Chinese

openprompt

An Open-Source Toolkit for Prompt-Learning.

paper_writing_tips

promptpapers

Must-read papers on prompt-based tuning for pre-trained language models.

proxypool

An Efficient ProxyPool with Getter, Tester and Server

python