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: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org