hankcs Goto Github PK

stanford_dl_ex

stanford_dl_ex-solutions

Deep neural network and deep convolutional network with AdaGrad and AdaDec

sub-character-cws

Sub-Character Representation Learning

sumy

Module for automatic summarization of text documents and HTML pages.

swne

Switchboard Named Entity Corpus

text-classification-svm

The missing SVM-based text classification module implementing HanLP's interface

textclassification

文本分类

textrank

TextRank算法提取关键词的Java实现

tmsvm

tree-viewer

A d3.js syntax tree viewer

treebankpreprocessing

Python scripts preprocessing Penn Treebank and Chinese Treebank

triehard

A generic compact Trie implementation in Java. Built for high-performance applications.

txt2vec

Txt2Vec is a toolkit to represent text by vector. It's based on Google's word2vec project.

udacity-deep-learning

Assignments for Udacity Deep Learning class with TensorFlow in PURE Python, not IPython Notebook

ufldl-tutorial

Deep Learning and Unsupervised Feature Learning Tutorial Solutions

ufldl_tutorial

Stanford Unsupervised Feature Learning and Deep Learning Tutorial

viterbi

An implementation of HMM-Viterbi Algorithm 通用的维特比算法实现

web-data

The repo to host all the web data including images for documents in dmlc projects.

word2vec

word2vec的Java并行实现

word2vec-c11

Word2Vec in C++ 11

word2vec-cmake

word2vec-doc2vec

An extension of word2vec to efficiently represent new text as vectors. New text can be query, sentence and paragraph.

word2vec-google

Google's word2vec with CMake configuration

word2vec-lucene

This tool extracts word vectors from Lucene index.

word2vec-sentiments

Tutorial for Sentiment Analysis using Doc2Vec in gensim (or "getting 87% accuracy in sentiment analysis in under 100 lines of code")

zanata-platform

Zanata is a web-based system for translators to translate documentation and software online using a web browser.