kai's repositories
ansj_seg
ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典
bdbk-kb
Baidu Baike Knowledge base
ChineseEntityLinking
Chinese entity linking with freebase
CoreNLP
Stanford CoreNLP: A Java suite of Core NLP tools
Crepe
Character-level Convolutional Networks for Text Classification
DL-Learner
A tool for supervised Machine Learning in OWL and Description Logics
DSSM
An reimplementation of Microsoft DSSM
eesen
End-to-End Speech Recognition using Deep RNNs (Models), CTC (Training) and WFSTs (Decoding)
keyword-search
keyword-search
libsvm-dp
Document preprocessing for preparing formatted input data which is suitable for LibSVM tool.
lstm-2
Minimal, clean example of lstm neural network training in python, for learning purposes.
lstm-char-cnn
LSTM language model with CNN over characters
neural-networks-and-deep-learning
Code samples for my book "Neural Networks and Deep Learning"
nlp-lang
这个项目是一个基本包.封装了大多数nlp项目中常用工具
opendial
A generic Java toolkit for building dialogue systems
sego
Go中文分词
shadowsocks
Shadowsocks for Linux
snownlp
Python library for processing Chinese text
speech-language-processing
A curated list of speech and natural language processing resources
sqlitetools
sqlite3 tools for java
uima-chinese-segmenter
A UIMA Analysis Engine to tokenize a chinese text into a sequence of chenese words
WikiParser
Some tools that parse wikipedia dump file
word
Java分布式中文分词组件 - word分词
yodaqa
A Question Answering system built on top of the Apache UIMA framework.