Skip to content

John Snow Labs Spark-NLP 2.5.3: Detect Fake news, emotions, spams, and more classification models, enhancements, and bug fixes

Compare
Choose a tag to compare
@maziyarpanahi maziyarpanahi released this 03 Jul 18:57
· 4908 commits to master since this release

Overview

We are very happy to release Spark NLP 2.5.3 with 5 new pre-trained ClassifierDL models for multi-class text classification. There are also bug-fixes and other enhancements introduced in this release which were reported and requested by Spark NLP users.

As always, we thank our community for their feedback, questions, and feature requests.


New Features

  • TextMatcher now can construct the chunks from tokens instead of the original documents via buildFromTokens param
  • CoNLLGenerator now is accessible in Python

Bugfixes

  • Fix a bug in ContextSpellChecker resulting in IllegalArgumentException

Enhancements

  • Improve RocksDB connection to support different storage capabilities
  • Improve parameters naming convention in ContextSpellChecker
  • Add NerConverter to documentation
  • Fix multi-language tabs in documentation

Models

We have added 5 new pre-trained ClassifierDL models for multi-class text classification.

Model Name Build Lang Description Offline
ClassifierDLModel classifierdl_use_spam 2.5.3 en Detect if a message is spam or not Download
ClassifierDLModel classifierdl_use_fakenews 2.5.3 en Classify if a news is fake or real Download
ClassifierDLModel classifierdl_use_emotion 2.5.3 en Detect Emotions in TweetsDetect Emotions in Tweets Download
ClassifierDLModel classifierdl_use_cyberbullying 2.5.3 en Classify if a tweet is bullying Download
ClassifierDLModel classifierdl_use_sarcasm 2.5.3 en Identify sarcastic tweets Download

Documentation

  • Update documentation for release of Spark NLP 2.5.x
  • Update the entire spark-nlp-workshop notebooks for Spark NLP 2.5.x
  • Update the entire spark-nlp-models repository with new pre-trained models and pipelines

Installation

Python

#PyPI

pip install spark-nlp==2.5.3

#Conda

conda install -c johnsnowlabs spark-nlp==2.5.3

Spark

spark-shell --packages com.johnsnowlabs.nlp:spark-nlp_2.11:2.5.3

PySpark

pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.11:2.5.3

Maven

<dependency>
    <groupId>com.johnsnowlabs.nlp</groupId>
    <artifactId>spark-nlp_2.11</artifactId>
    <version>2.5.3</version>
</dependency>

FAT JARs