January 2, 2020

255 words 2 mins read

How machine learning with open source tools helps everyone build better products

How machine learning with open source tools helps everyone build better products

Michelle Casbon explores the machine learning and natural language processing that enables teams to build products that feel native to every user and explains how Qordoba is tackling the underserved domain of localization using open source tools, including Kubernetes, Docker, Scala, Apache Spark, Apache Cassandra, and Apache PredictionIO (incubating).

Talk Title How machine learning with open source tools helps everyone build better products
Speakers Michelle Casbon (Google)
Conference Strata Data Conference
Conf Tag Make Data Work
Location New York, New York
Date September 26-28, 2017
URL Talk Page
Slides Talk Slides
Video

Building products that feel native to every user, regardless of language, is the best way to establish a user base across the globe. To do this, a product needs to support a variety of locales. The challenge with supporting multiple locales is the maintenance and generation of localized strings, which are deeply integrated into many facets of a product. Michelle Casbon explores the machine learning and natural language processing that enables Qordoba to generate high-quality translations in many different languages and describes the techniques Qordoba uses to provide continuous deployment of localized strings, live syncing across platforms (mobile, web, Photoshop, Sketch, Help Desk, etc.), content generation for any locale, and emotional response. Michelle also explores Qordoba’s architecture for handling billions of localized strings in many different languages, using Apache Spark and Apache PredictionIO (incubating) for natural language processing, Kubernetes and Docker for containerized deployment, scaling, and management, Apache Cassandra and MariaDB as a storage layer, and Scala and Akka as an orchestration layer.

comments powered by Disqus