kejunxiao

NLP/recommender system/deep learning

Beijing,China

Pinned Repositories

sparse_btm
a cpp implementation of sparse biterm topic model, 10x faster than origin implementation because using sparse-sampler.
Language:C++7 2 11
sparse_hlda
a fast Cpp-implementation Hierarchy Latent Dirichlet Allocation algorithm, can aggregate stop-words/meaningless-high-frequency-words into "common-topic"(a rubbish words bucket) and generate K(number of topics you set) more pure "special-topics".
Language:C++2 1 01
TextClf
text classify; tensorflow; cnn; rnn
Language:Python0 0 00

kejunxiao's Repositories

kejunxiao/sparse_btm
a cpp implementation of sparse biterm topic model, 10x faster than origin implementation because using sparse-sampler.
Language:C++7 2 11
kejunxiao/sparse_hlda
a fast Cpp-implementation Hierarchy Latent Dirichlet Allocation algorithm, can aggregate stop-words/meaningless-high-frequency-words into "common-topic"(a rubbish words bucket) and generate K(number of topics you set) more pure "special-topics".
Language:C++2 1 01
kejunxiao/TextClf
text classify; tensorflow; cnn; rnn
Language:Python0 0 00