You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@spark.apache.org by "Liang-Chi Hsieh (JIRA)" <ji...@apache.org> on 2015/05/20 19:37:59 UTC

[jira] [Created] (SPARK-7764) Add negative sampling to Word2Vec

Liang-Chi Hsieh created SPARK-7764:
--------------------------------------

             Summary: Add negative sampling to Word2Vec
                 Key: SPARK-7764
                 URL: https://issues.apache.org/jira/browse/SPARK-7764
             Project: Spark
          Issue Type: Improvement
          Components: MLlib
            Reporter: Liang-Chi Hsieh


The paper [1] proposed negative sampling approach that is more efficient than hierarchical softmax for training Word2Vec model. This ticket is proposed to add the support of negative sampling to current Word2Vec implementation.

[1] Tomas Mikolov et al., "Distributed Representations of Words and Phrases and their Compositionality"



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org