流川枫's repositories
WordEmbedding
有关词向量相关的知识,例如:word2vec、ELMo
ChineseNlpCorpus
搜集、整理、发布 中文 自然语言处理 语料/数据集,与 有志之士 共同 促进 中文 自然语言处理 的 发展。
500lines
500 Lines or Less
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
dgcnn_for_reading_comprehension
keras implement of dgcnn for reading comprehension
from_coder_to_expert
2019年最新总结,从程序员到CTO,从专业走向卓越,分享大牛企业内部pdf与PPT
fullstack-data-engineer
全栈数据工程师养成攻略
fuzzywuzzy
Fuzzy String Matching in Python
How-to-Deploy-a-Tensorflow-Model-in-Production
This is the code for the "How to Deploy a Tensorflow Model in Production" by Siraj Raval on YouTube
learning_to_rank
利用lightgbm做(learning to rank)排序学习,包括数据处理、模型训练、模型决策可视化、模型可解释性以及预测等。
MachineLearning
Machine learning resources,including algorithm, paper, dataset, example and so on.
MLDemo
This repo is all the machine learning related project codes and their corresponding blog posts at the graduate level.
nlp_course
YSDA course in Natural Language Processing
NLP_DataSet
搜集NLP任务相关辅助数据集
onefraction
React/ApolloGraphQL/Node/Mongo demo written in Typescript
Palmetto
Palmetto is a quality measuring tool for topics
pkuseg-python
python版本:领域细分的中文分词工具,简单易用,跟现有开源工具相比提高了分词的准确率。
rec_system
推荐系统,内含主流模型,不定期更新模型
Reco-papers
Classic papers and resources on recommendation
Spellcorrection
搜索引擎多候选词推荐
Structured-Self-Attention
A Structured Self-attentive Sentence Embedding
TextMining
某电商手机评论的文本挖掘初体验 功能板块:数据预处理、LDA模型获取特征词、情感极性判断与程度计算、回归模型预测销量排序
wide-and-deep-learning-keras
Wide and Deep Learning implemented with Keras