Natural language processing (NLP) is a key component in many data science systems that need to identify and understand critical information out of a sea of unstructured data. 

But, how can you gain the maximal value from NLP to support your business objectives, especially for near-real-time use cases? 

In this webinar David Talby, CTO of Pacific AI, will introduce the Spark Natural Language Processing library which natively extends the Spark ML Pipeline API, and allows for a scalable approach within a distributed large scale environment.

David will describe and present:

• Open source Spark NLP library benefits
• Infrastructure requirements needed to deploy ML models in business operations
• Common use cases including entity recognition, sentiment analysis dependency parsing, de-identification, OCR, and natural language BI 

Yoav Einav, VP Product of GigaSpaces, will present a case study of how a leading IT service provider for financial firms is leveraging NLP to match cases on their CRM system to live service calls. The system responds with sub-second latency and is able to create continuous learning models based on each transaction, ensuring the most updated models for smarter and faster insights.