Word2Vec Visualizer

This tool helps you visualize, query and explore Word2Vec models. Word2Vec is a deep learning technique that feeds massive amounts of text into a shallow neural net which can then be used to solve a variety of NLP and ML problems.

Word2Vec Visualizer uses Gensim to list and compare vectors and it uses t-SNE to visualize a dimensional reduction of the vector space. Scikit-Learn is used for K-Means clustering.

Setup

Just use the pre-built docker image on docker hub cunum/word2vec-visualizer and directly jump to step Usage or clone the project and build the docker image yourself by running in project directory

docker build . -t cunum/word2vec-visualizer

Usage

A) Run with a pre-trained model

docker run -p 8080:8080 -v /path/to/word2vec.model:/word2vec.model cunum/word2vec-visualizer

B) Run with text documents (used to train a model on startup)

docker run -p 8080:8080 -v /path/to/documents:/documents cunum/word2vec-visualizer

Now point your browser at http://localhost:8080 to load the explorer

Obtaining pre-trained models

A classic example of Word2Vec is the Google News model trained on 600M sentences

• GoogleNews-vectors-negative300.bin.gz

• More models