largelymfs/topical_word_embeddings

A demo code for topical word embedding

topical_word_embeddings's Issues

Cannot reproduce the result due to exceptions and what is the parameter setting?

hi all,
I tried this code, got many problems:
1, What is the parameter setting of GibbsLDA to reproduce paper's result?
2, UserWarning: Cython compilation failed, training will be slow. Do you have Cython installed? pip install cython
3, File "/home/sbai/Downloads/topical_word_embeddings-master/TWE-1/gensim/models/word2vec.py", line 901, in
job_words = sum(train_sentence_topic(self, sentence, alpha, work) for sentence in job)
NameError: global name 'train_sentence_topic' is not defined

environment: ubuntu14.04 python2.7 64bit.

twe-1: in except-except branch, train_sentence_topic not defined

topical_word_embeddings/TWE-1/gensim/models/word2vec.py", line 901
NameError: global name 'train_sentence_topic' is not defined

TWE-1结果如何使用

请问在用TWE-1代码得到word_vector.txt和topic_vector.txt文件后，如何计算得到topical word embeddings？

TWE-1 train failed

python train.py wordmap tassign topic_number
/topical_word_embeddings-master/TWE-1/gensim/models/word2vec.py:405: UserWarning: Cython compilation failed, training will be slow. Do you have Cython installed? pip install cython
warnings.warn("Cython compilation failed, training will be slow. Do you have Cython installed? `pip install cython

but i have installed the cython, anything else should I do ?

Exception when running TWE3

I'm running TWE1 and TWE2 successfully, but failed when running TW3, the printed result is shown as below.Does anyone meet same problem? Hopefully can get the answer.