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

Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2015/05/14 19:37:59 UTC

[jira] [Commented] (SPARK-7641) Add subsampling of frequent words for Word2Vec

    [ https://issues.apache.org/jira/browse/SPARK-7641?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14544081#comment-14544081 ] 

Apache Spark commented on SPARK-7641:
-------------------------------------

User 'viirya' has created a pull request for this issue:
https://github.com/apache/spark/pull/6151

> Add subsampling of frequent words for Word2Vec
> ----------------------------------------------
>
>                 Key: SPARK-7641
>                 URL: https://issues.apache.org/jira/browse/SPARK-7641
>             Project: Spark
>          Issue Type: Improvement
>          Components: MLlib
>            Reporter: Liang-Chi Hsieh
>
> According to the paper [1], subsampling frequent words can accelerate learning and signiﬁcantly improves the accuracy of the learned vectors. This ticket is proposed to add it into current Word2Vec.
> [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