[VIRTUAL] Natural Language Processing at Scale with SparkNLP

Natural language processing (NLP) has come to the forefront of the data and AI space, given the recent explosion in generative AI and large language models. While traditional NLP has existed for decades, how are these techniques applied in the world of Big Data? The SparkNLP library from John Snow Labs has become a de facto standard for doing NLP work at scale, and is widely used within the medical and healthcare domains, where making sense of large volumes of unstructured text data is a challenging and fundamental problem.

In this meetup, we'll be introduced to the field of NLP at a high level and see an overview of SparkNLP's capabilities applied to different common NLP tasks. We'll work hands-on with SparkNLP pipelines in pyspark, applying text preprocessing, named entity recognition, and other techniques which are part of a natural language processing workflow. Finally, we will look at what is available in the SparkNLP ecosystem and recent developments in the library integrating it with emerging tools and models in the generative AI and LLM space.

This will be a virtual event hosted on Google meet.

Agenda:

• 5:30 PM - Welcome
• 5:40 PM - Presentation

About the speaker: Myles Harrison is a data scientist, trainer, and the founder of NLP from scratch, an independent provider of accelerated training in natural language processing, large language models, and generative AI. Prior to this, he was a lead instructor and team lead at a data science bootcamp and delivered over two thousand hour of in-person and online training in data science, machine learning, and Big Data for students from diverse backgrounds looking to transform their careers and break into data science professionally.