Word2vec models trained on English Wikipedia

<p>This repository contains Word2Vec models trained on the full text of the English Wikipedia as downloaded in December 2021.</p> <p>Preprocessing:</p> <ul> <li>lowercasing</li> <li>n-grams up to 4-grams were computed using Bouma 2009&nbsp;(https://svn.spraakdata.gu.se/repos/gerlof/pub/www/Docs/npmi-pfd.pdf),&nbsp;min freq threshold of 10</li> </ul> <p>Two models, trained with Gensim:</p> <ul> <li>wiki_300_5_word2vec --&gt; dim 300, freq threshold 5</li> <li>wiki_300_50_word2vec &nbsp;--&gt; dim 300, freq threshold 50</li> </ul> <p>Other hyperparameters set as follows: window=5, epochs=5, seed=1830, sg=1</p> <p>Note:<br> Machine learning models trained on uncurated data inevitably learn hidden or obvious biases and as a result, the models shared with here might&nbsp;contain characteristics&nbsp;including sexism, racism, antisemitism, homophobia, and other such types of unacceptable biases. I encourage whoever is using these models to make sure such biases are actually removed before using them in production settings (see eg https://aclanthology.org/N19-1061/)</p>