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: [email protected]
For additional commands, e-mail: [email protected]
