Abstract: 

This is a hands-on tutorial on applying the latest advances in deep learning and transfer learning for common NLP tasks such as named entity recognition, document classification, spell checking, and sentiment analysis. Learn to building complete text analysis pipelines using the highly accurate, high performant, open-source Spark NLP library in Python.

This is a hands-on tutorial on applying the latest advances in deep learning and transfer learning for common NLP tasks such as named entity recognition, document classification, spell checking, and sentiment analysis. Learn to building complete text analysis pipelines using the highly accurate, high performant, open-source Spark NLP library in Python.

Spark NLP provides state-of-the-art accuracy, speed, and scalability for natural language processing by delivering production-grade implementations of some of the most recent research in applied deep learning and transfer learning. It is the most widely used NLP library in the enterprise today.

Session Outline
This tutorial will walk you, through a set of executable Python notebooks that you will edit and extend, through implementing these common natural language processing tasks:

1. Named entity recognition
2. Document classification
3. Sentiment analysis
4. Spell checking and correction
5. Training your own domain-specific and language-specific models
6. Multi-language support

Background Knowledge
This tutorial is intended for practicing data scientists and NLP engineers building state-of-the-art AI applications in industry. The discussion of each NLP task will include the latest advances in deep learning to tackle it, including the pre-built use of Universal Sentence Encoders, ALBERT, XLNet, BERT, and other embeddings built-in within Spark NLP.

Bio: 

David Talby is a chief technology officer at Pacific AI, helping fast-growing companies apply big data and data science techniques to solve real-world problems in healthcare, life science, and related fields. David has extensive experience in building and operating web-scale data science and business platforms, as well as building world-class, Agile, distributed teams. Previously, he was with Microsoft’s Bing Group, where he led business operations for Bing Shopping in the US and Europe and worked at Amazon both in Seattle and the UK, where he built and ran distributed teams that helped scale Amazon’s financial systems. David holds a Ph.D. in computer science and master’s degrees in both computer science and business administration.