Architecture of an NLP Deployment - Michele Casbon

No machine learning tool is an island. The purpose of any predictive model is to provide information and influence specific actions. The intent is to drive decisions that accomplish goals. This talk will give you enough information to either improve your existing architecture or affirm the decisions you have already made. Natural Language Processing is used as an example, but the concepts apply to broader forms of Machine Intelligence.

This talk explores the deployment of machine learning models as part of a larger system. The existing environment has an influence on available options. We will look at the different functional components and how they interact with each other, as well as the impact they have on the bigger picture.

For each component, we will explore the pros & cons of various approaches, ultimately landing on a reference architecture that has proven to be flexible, scalable, and resilient in production environments.
--
Michelle Casbon is a Senior Engineer on the Google Cloud Platform Developer Relations team, where she focuses on open source contributions and community engagement for machine learning and big data tools. Prior to joining Google, she was at several San Francisco-based startups as a Senior Engineer and Director of Data Science. Within these roles, she built and shipped machine learning products on distributed platforms using both AWS and GCP. Michelle’s development experience spans more than a decade and has primarily focused on multilingual natural language processing, system architecture and integration, and continuous delivery pipelines for machine learning applications. Michelle holds a masters degree from the University of Cambridge.