Details
-
New Feature
-
Status: Open
-
Major
-
Resolution: Unresolved
-
None
-
None
Description
Support Distributed Representation, word2vec.
- Original paper http://web2.cs.colmbia.edu/~blei/seminar/2016_discrete_data/readings/MikolovSutskeverChenCorradoDean2013.pdf
- word2vec Explained https://arxiv.org/pdf/1402.3722.pdf
- Network-Efficient Distributed Word2vec Training System for Large Vocabularies https://arxiv.org/abs/1606.08495
- Parallelizing Word2Vec in Shared and Distributed Memory https://pdfs.semanticscholar.org/cced/c38f68ffaf51cf8c31cd6c6b5c2cf033f91a.pdf
Implementations
- https://spark.apache.org/docs/latest/mllib-feature-extraction.html#word2vec
https://github.com/apache/spark/pull/1719 - https://github.com/deeplearning4j/deeplearning4j/blob/master/deeplearning4j-scaleout/spark/dl4j-spark-nlp/src/main/java/org/deeplearning4j/spark/models/embeddings/word2vec/Word2Vec.java
Attachments
Issue Links
- links to