https://github.com/fxia22/word2vec

Automatically exported from code.google.com/p/word2vec
https://github.com/fxia22/word2vec

Last synced: 1 day ago
JSON representation

Automatically exported from code.google.com/p/word2vec

• Host: GitHub
• URL: https://github.com/fxia22/word2vec
• Owner: fxia22
• License: apache-2.0
• Created: 2015-05-27T15:55:21.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2015-06-06T18:00:55.000Z (over 9 years ago)
• Last Synced: 2023-08-02T19:20:43.048Z (over 1 year ago)
• Language: C
• Size: 277 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 28
• Metadata Files:
  • Readme: README.txt
  • License: LICENSE

Awesome Lists containing this project

README

        
Tools for computing distributed representtion of words

------------------------------------------------------

We provide an implementation of the Continuous Bag-of-Words (CBOW) and the Skip-gram model (SG), as well as several demo scripts.

Given a text corpus, the word2vec tool learns a vector for every word in the vocabulary using the Continuous

Bag-of-Words or the Skip-Gram neural network architectures. The user should to specify the following:

 - desired vector dimensionality

 - the size of the context window for either the Skip-Gram or the Continuous Bag-of-Words model

 - training algorithm: hierarchical softmax and / or negative sampling

 - threshold for downsampling the frequent words 

 - number of threads to use

 - the format of the output word vector file (text or binary)

Usually, the other hyper-parameters such as the learning rate do not need to be tuned for different training sets. 

The script demo-word.sh downloads a small (100MB) text corpus from the web, and trains a small word vector model. After the training

is finished, the user can interactively explore the similarity of the words.

More information about the scripts is provided at https://code.google.com/p/word2vec/