wangdomg Goto Github PK

liblinear

libsvm

lightctr

Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based machine learning, philosophy of Parameter Server and Ring-AllReduce collective communication.

lihang

Statistical learning methods, 统计学习方法 [李航] 值得反复读. [笔记, 代码, notebook, 参考文献, Errata, lihang]

machine-learning-notes

周志华《机器学习》手推笔记

machine-learning-yearning-cn

Machine Learning Yearning 中文版 - 《机器学习训练秘籍》 - Andrew Ng 著

machine_learning

Some example machine learning algorithm implementations from Berkeley's CS 281A during Fall 2012.

muse

A library for Multilingual Unsupervised or Supervised word Embeddings

mycail

**法研杯-司法人工智能挑战赛

ner-based-on-bilstm-crf

用TensorFlow实现的基于双向LSTM+CRF的命名实体识别。

nndl.github.io

《神经网络与深度学习》 Neural Network and Deep Learning

open-ie-papers

Open Information Extraction (OpenIE) and Open Relation Extraction (ORE) papers and data.

openke

An Open-Source Package for Knowledge Embedding (KE)

opennmt-py

Open Source Neural Machine Translation in PyTorch

profpedia

ps-lite

A lightweight parameter server interface

python

All Algorithms implemented in Python

pythonwork

pytorch-language-model

Simple LSTM-based word-level language model in PyTorch

pytorch-pretrained-bert

📖The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.

pytorch-seq2seq

An open source framework for seq2seq models in PyTorch.

pytorch-tutorial

PyTorch Tutorial for Deep Learning Researchers

pytorch_chatbot

A Marvelous ChatBot implement using PyTorch.

qaonmilitarykg

QAonMilitaryKG，QaSystem based on military knowledge graph that stores in mongodb which is different from the previous one, 基于mongodb存储的军事领域知识图谱问答项目，包括飞行器、太空装备等8大类，100余小类，共计5800项的军事武器知识库，该项目不使用图数据库进行存储，通过jieba进行问句解析，问句实体项识别，基于查询模板完成多类问题的查询，主要是提供一种工业界的问答**demo。

sa-sent

Implementation for SA-LSTM

sentiment

CCF大数据比赛，基于主题的文本情感分析

sentimentpolarityanalysis

情感极性分析repository1：基于情感词典、k-NN、Bayes、最大熵、SVM的情感极性分析。

skiprnn_pytorch

A pytorch implementation of the paper: "Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks"

smae

This is the code for "Learning Sentiment Memories for Sentiment Modification without Parallel Data".

sociallistening

依据香港中文大学设计的规则系统，先用小样本评论建立初始关键词库，再结合18种句式逐条匹配评论，能够快速准确地识别评论对象及情感极性。经多次迭代优化关键词库后，达到较高准确率的基础上，使用Tableau进一步分析数据，识别出客户集中关注的商品属性、普遍好评差评的商品属性；通过与同类商品竞品分析，识别出商品的优缺点，画出商品属性特征风险区、改进区、保持区和低人气区分布图；最终撰写分析报告，供电商经营参考。