(Word embeddings)
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/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/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]
 
* [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===
 

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

GloVe

pre trained models