HHself

chinese_wubi

中文 五笔字型码 拼音相互转换工具 中文语料转换后可以直接应用于字符级自然语言模型中

insuranceQA-cnn-lstm

tensorflow and theano cnn code for insurance QA(question Answer matching)

plda

Automatically exported from http://code.google.com/p/plda

random-walk-lda

analysisWeibo

This is my graduation project, which contains the analysis about sina weibo.

Author-Biterm-Topic-Model

This code are based on Biterm Topic Model(https://github.com/xiaohuiyan/BTM)

CLSM

This code is for Convolutional Latent Semantic Model, which is similay with DSSM(Deep Semantic Similarity Model).

keyword-extraction-datasets

Different datasets for developing and testing keyword extraction algorithms

lda

Topic modeling with latent Dirichlet allocation