Code for the blog post "Making Sense of Word2vec"
Python Shell
Permalink
Failed to load latest commit information.
README.md update docs Dec 20, 2014
cooccur_matrix.pyx add README Dec 20, 2014
run_all.sh update docs Dec 20, 2014
run_embed.py improve cython dynamic import Dec 24, 2014
run_glove.py add README Dec 20, 2014
run_ppmi.py add README Dec 20, 2014
run_svd.py add README Dec 20, 2014
run_word2vec.py add README Dec 20, 2014

README.md

Evaluation of word embeddings

Code for the blog post evaluating word2vec, GloVe, SPPMI and SPPMI-SVD methods:

Making sense of word2vec.

Run run_all.sh to run all experiments. Logs with results will be stored in the data directory.

To replicate my results from the blog article, download and preprocess Wikipedia using this code. You can use your own corpus though (the corpus path is a parameter to run_all.sh).