This directory contains models for unsupervised training of word embeddings using the model described in:

(Mikolov, et. al.) Efficient Estimation of Word Representations in Vector Space, ICLR 2013.

Detailed instructions on how to get started and use them are available in the tutorials. Brief instructions are below.

• Word2Vec Tutorial

To download the example text and evaluation data:

wget http://mattmahoney.net/dc/text8.zip -O text8.zip
unzip text8.zip
wget http://download.tensorflow.org/data/questions-words.txt

Assuming you are using the pip package install and have cloned the git repository, navigate into this directory and run using:

cd tensorflow/models/embedding
python word2vec_optimized.py \
  --train_data=text8 \
  --eval_data=questions-words.txt \
  --save_path=/tmp/

To run the code from sources using bazel:

bazel run -c opt tensorflow/models/embedding/word2vec_optimized -- \
  --train_data=text8 \
  --eval_data=questions-words.txt \
  --save_path=/tmp/

Here is a short overview of what is in this directory.