Context This is a record of the word embeddings and related files from: - http://www-nlp.stanford.edu/~ehhuang/SCWS.zip - http://www-nlp.stanford.edu/~ehhuang/wordrep.zip - http://www-nlp.stanford.edu/~ehhuang/trainEmb.zip **Lost**: This archive is created because the main site http://ai.stanford.edu/%E2%88%BCehhuang/ gone with the wind and is now a 404. Also the https://nlp.stanford.edu/~ehhuang/ is no longer maintained and prints a `test` message. The last known cache version of the site is on http://webcache.googleusercontent.com/search?q=cache:N0iXkrYS2hUJ:ai.stanford.edu/~ehhuang/+&cd=3&hl=en&ct=clnk&gl=sg (saved as `.htm` file) **Found** (22 March 2019): The new site is hosted on http://ai.stanford.edu/~ehhuang/index.html Content This dataset contains the original models and some code files for the **[Improving Word Representations via Global Context and Multiple Word Prototypes](http://www.aclweb.org/anthology/P12-1092)** Acknowledgements All credits goes to Eric H. Huang. Please cite the following if you use it: @InProceedings{P12-1092, author = "Huang, Eric and Socher, Richard and Manning, Christopher and Ng, Andrew