NLP/Text Analytics: Spark ML & Pipelines, Stanford CoreNLP, Succint, KeystoneML

This is a past event

430 people went

Location image of event venue

Details

Abstract

Come enjoy this "meetup-turned-mini-conference" (free, as always) covering many aspects of Information Retrieval, Search, NLP, and Text-based Advanced Analytics with Spark including the following:

4 Talks!!

1) Training & Serving NLP/Spark ML Models in a Distributed Cloud-based Infrastructure

Michelle Casbon (Idibon)

2) Berkeley AMPLab Project Succinct: Search + Spark

Rachit Agarwal (Berkeley AMPLab)

3) Google's Word2Vec and Spark

Marek Kolodziej (Nitro)

4) Spark ML, ML Pipeline, LDA Topic Analysis, Word2Vec, Stanford CoreNLP, and Keystone ML

Chris Fregly (IBM Spark Tech Center)

Relevant Links

http://idibon.com/ (https://code.google.com/p/word2vec/)

https://github.com/amplab/succinct (https://code.google.com/p/word2vec/)

https://code.google.com/p/word2vec/

http://spark.apache.org/docs/latest/mllib-feature-extraction.html#word2vec

http://stanfordnlp.github.io/CoreNLP/ (http://nlp.stanford.edu/software/corenlp.shtml)

https://github.com/databricks/spark-corenlp

http://keystone-ml.org/ (http://blog.cloudera.com/blog/2015/08/using-apache-spark-for-massively-parallel-nlp-at-tripadvisor/)

http://blog.cloudera.com/blog/2015/08/using-apache-spark-for-massively-parallel-nlp-at-tripadvisor/

https://www.youtube.com/watch?v=pIMs946Eu2U