John Snow Labs announces new version of Spark NLP
John Snow Labs has announced immediate availability of the new version of Spark NLP, a widely used natural language processing library. The library can be used from Python, Java, and Scala APIs and comes with more than 150 pre-trained models & pipelines.
John Snow Labs is an AI and NLP company that works to accelerate progress in data science by providing models, data, and platforms. Founded in 2015, through its offerings, the firm assists healthcare and life sciences industries to build, scale, deploy, and operate AI products and services (through on-premise or cloud architectures) in order to collect and prepare patient data for analysis.
“When we started planning for Spark NLP 2.5 a few months ago, the world was a different place. We have been blown away by the use of natural language processing for early outbreak detections, question-answering chatbot services, text analysis of medical records, monitoring efforts to minimize the spread of COVID-19, and many more.” said Maziyar Panahi, a data scientist at John Snow Labs and a lead contributor to Spark NLP.
Spark NLP 2.5 is an additional major step in John Snow Labs' efforts to provide the open source community with accurate NLP algorithms and models. By making the most recent academic advances available as a production-grade, scalable, and trainable software library, the global data science community can make faster progress towards putting AI to good use.
Key advancements include ALBERT (a Lite BERT) and XLNet embeddings, a new, trainable, deep-learning-based spell checking algorithm that takes into account a word’s context before recommending how to correct it, new deep-learning sentiment analysis, expansion of the deep-learning document classification annotator, and more.
For more information, go to www.johnsnowlabs.com.