MrHungry

HanLP

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 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

jd-base

京东薅羊毛脚本 https://github.com/LXK9301/jd_scripts 的shell套壳工具

my_delf

reimplement delf attention train

xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow

2016CCF_BDCI_Sougou

【源码以及PPT分享】2016CCF大数据与计算智能大赛：精准营销中搜狗用户画像挖掘

O2O-Coupon-Usage-Forecast

1st Place Solution for O2O Coupon Usage Forecast

char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

tensorflow

Computation using data flow graphs for scalable machine learning

deep-reinforcement-learning-papers

A list of recent papers regarding deep reinforcement learning

CNN-yelp-challenge-2016-sentiment-classification

code for training a word level CNN for sentiment classification on yelp's review dataset 2016.

music_prediction

learngit

gitskills_test

kenlm

KenLM: Faster and Smaller Language Model Queries

rnnpg

Code for Chinese Poetry Generation with Recurrent Neural Networks (EMNLP 2014)

msohu-backup

backup http://m.sohu.com one time every 60s

reality-of-Dream-of-Red-Mansions

Comparision analysis of words use between 1~80 chapters and 80~120 chapters of 《A Dream of Red Mansions》.

LDA4j

A Java implemention of LDA(Latent Dirichlet Allocation)

gitskills