Pinned Repositories
ChineseWordSegmentation
Segment Chinese sentences into separated words.
DrawingLottery
This is necessary for you when a year ends and the next starts.
HiddenMarkovModel
A simple implentation of HMM.
jMeny
A jQuery-based multiple menu capable of page flipping to support many elements in one level. It is still in development. It now uses some icons based on Bootstrap. I will replace them later.
K-meansCluster
A java implementation of k-means algorithm.It uses ball tree as internal data structure to accelerate the computation.It uses 2-norm distance to compute the similarity between instances.
LilyPinyinInputMethod
A java implemented Pinyin Input method.It is a team project for my natural language processing course which I am the leader.It now uses a pinyin table downloaded at(http://www.datatang.com/data/11858) and a reduced corpus from Sogou Corp. which you can download at (http://www.sogou.com/labs/dl/c.html) .Have fun!
Naive-Bayes-Classifier
A simple implemantation by Octave of naive Bayes Classifier,with a hypothesis that the continuous values associated with each class are distributed according to a Gaussian distribution.
PYSeparator
Separate a String to syllybles(single legal Pinyin) most likely to possible intension of users.You should provide the function of a dictionary by implementing the dict interface.
skyline0623.github.io
My blog built by hexo.
SpellingCorrector
Based on the blog "How to Write a Spelling Corrector" by Peter Norvig,I implement a Java version of it.Further work will be focused on improving the error model.This implementation has a assumption that the word with an edit distance of 1 to the oringinal is more likely than the one with distance of 2.That may not be true for many cases.
skyline0623's Repositories
skyline0623/K-meansCluster
A java implementation of k-means algorithm.It uses ball tree as internal data structure to accelerate the computation.It uses 2-norm distance to compute the similarity between instances.
skyline0623/LilyPinyinInputMethod
A java implemented Pinyin Input method.It is a team project for my natural language processing course which I am the leader.It now uses a pinyin table downloaded at(http://www.datatang.com/data/11858) and a reduced corpus from Sogou Corp. which you can download at (http://www.sogou.com/labs/dl/c.html) .Have fun!
skyline0623/PYSeparator
Separate a String to syllybles(single legal Pinyin) most likely to possible intension of users.You should provide the function of a dictionary by implementing the dict interface.
skyline0623/ChineseWordSegmentation
Segment Chinese sentences into separated words.
skyline0623/DrawingLottery
This is necessary for you when a year ends and the next starts.
skyline0623/HiddenMarkovModel
A simple implentation of HMM.
skyline0623/jMeny
A jQuery-based multiple menu capable of page flipping to support many elements in one level. It is still in development. It now uses some icons based on Bootstrap. I will replace them later.
skyline0623/Naive-Bayes-Classifier
A simple implemantation by Octave of naive Bayes Classifier,with a hypothesis that the continuous values associated with each class are distributed according to a Gaussian distribution.
skyline0623/skyline0623.github.io
My blog built by hexo.
skyline0623/SpellingCorrector
Based on the blog "How to Write a Spelling Corrector" by Peter Norvig,I implement a Java version of it.Further work will be focused on improving the error model.This implementation has a assumption that the word with an edit distance of 1 to the oringinal is more likely than the one with distance of 2.That may not be true for many cases.