Shubham Chopra created SPARK-20902:
--------------------------------------
Summary: Word2Vec implementations with Negative Sampling
Key: SPARK-20902
URL: https://issues.apache.org/jira/browse/SPARK-20902
Project: Spark
Issue Type: Improvement
Components: ML, MLlib
Affects Versions: 2.1.1
Reporter: Shubham Chopra
Spark MLlib Word2Vec currently only implements Skip-Gram+Hierarchical softmax.
Both Continuous bag of words (CBOW) and SkipGram have shown comparative or
better performance with Negative Sampling. This umbrella JIRA is to keep a
track of the effort to add negative sampling based implementations of both CBOW
and SkipGram models to Spark MLlib.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
