Added unk vectors to wordvec downloads

ellenzhuwang · Dec 30, 2015 · 72b8433 · 72b8433
1 parent f33bf82
commit 72b8433
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -15,10 +15,10 @@ Pre-trained word vectors are made available under the <a href="http:https://opendataco
 and License</a>
 <div class="entry">
 <ul style="padding-left:0px; margin-top:0px; margin-bottom:0px">
- <li> <a href="http:https://dumps.wikimedia.org/enwiki/20140102/">Wikipedia 2014</a> + <a href="https://catalog.ldc.upenn.edu/LDC2011T07">Gigaword 5</a> (6B tokens, 400K vocab, uncased, 50d, 100d, 200d, &amp; 300d vectors, 822 MB download): <a href="http:https://nlp.stanford.edu/data/glove.6B.zip">glove.6B.zip</a> </li>
- <li> Common Crawl (42B tokens, 1.9M vocab, uncased, 300d vectors, 1.75 GB download): <a href="http:https://nlp.stanford.edu/data/glove.42B.300d.zip">glove.42B.300d.zip</a> </li>
- <li> Common Crawl (840B tokens, 2.2M vocab, cased, 300d vectors, 2.03 GB download): <a href="http:https://nlp.stanford.edu/data/glove.840B.300d.zip">glove.840B.300d.zip</a> </li>
- <li> Twitter (2B tweets, 27B tokens, 1.2M vocab, uncased, 25d, 50d, 100d, &amp; 200d vectors, 1.42 GB download): <a href="http:https://nlp.stanford.edu/data/glove.twitter.27B.zip">glove.twitter.27B.zip</a> Ruby <a href="preprocess-twitter.rb">script</a> for preprocessing Twitter data </li>
+ <li> <a href="http:https://dumps.wikimedia.org/enwiki/20140102/">Wikipedia 2014</a> + <a href="https://catalog.ldc.upenn.edu/LDC2011T07">Gigaword 5</a> (6B tokens, 400K vocab, uncased, 50d, 100d, 200d, &amp; 300d vectors, 822 MB download): <a href="http:https://nlp.stanford.edu/data/wordvecs/glove.6B.zip">glove.6B.zip</a> </li>
+ <li> Common Crawl (42B tokens, 1.9M vocab, uncased, 300d vectors, 1.75 GB download): <a href="http:https://nlp.stanford.edu/data/wordvecs/glove.42B.300d.zip">glove.42B.300d.zip</a> </li>
+ <li> Common Crawl (840B tokens, 2.2M vocab, cased, 300d vectors, 2.03 GB download): <a href="http:https://nlp.stanford.edu/data/wordvecs/glove.840B.300d.zip">glove.840B.300d.zip</a> </li>
+ <li> Twitter (2B tweets, 27B tokens, 1.2M vocab, uncased, 25d, 50d, 100d, &amp; 200d vectors, 1.42 GB download): <a href="http:https://nlp.stanford.edu/data/wordvecs/glove.twitter.27B.zip">glove.twitter.27B.zip</a> Ruby <a href="preprocess-twitter.rb">script</a> for preprocessing Twitter data </li>
 </ul>
 </div>