GMU:The Hidden Layer:Topics: Difference between revisions

Revision as of 09:53, 8 May 2017

General Information on word embeddings

For a general explanation look here: [1]

Word2vec

Made by Google, uses Neural Net, performs good on semantics.

Installation + getting started:

pip install gensim

Fastword

Made by Facebbok based on word2vec. Better at capturing syntactic relations (like apparent ---> apparently) see here: [2] Pretrained model files are HUGE

@@ Line 1: / Line 1: @@
-== Word embeddings ==
+== General Information on word embeddings ==
+For a general explanation look here:
+[https://blog.acolyer.org/2016/04/21/the-amazing-power-of-word-vectors/]
+==Word2vec==
+Made by Google, uses Neural Net, performs good on semantics.
+=== Installation + getting started: ===
+pip install gensim
-=== pre trained models ===
+==Fastword==
+Made by Facebbok based on word2vec. Better at capturing syntactic relations (like apparent ---> apparently) see here:
+[https://rare-technologies.com/fasttext-and-gensim-word-embeddings/]
+Pretrained model files are HUGE
+==GloVe==
+== pre trained models ==
 * [https://github.com/Kyubyong/wordvectors https://github.com/Kyubyong/wordvectors: Word2Vec and FastText, Multiple languages, no english, trained on Wikipedia]
 * [https://github.com/3Top/word2vec-api#where-to-get-a-pretrained-models https://github.com/3Top/word2vec-api Mostly GloVe, some word2vec, English, Trained on News, Wikipedia, Twitter]
 * [https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md: Fasttext, all imaginable languages, trained on Wikipedia]
-===Word2vec===
-===GloVe===
-===Fastword===