Document Vectors in the Wild with James Dreiss

800 800 This Week in Machine Learning & AI

In this episode of our Strata Data series we’re joined by James Dreiss, Senior Data Scientist at international news syndicate Reuters.

James and I sat down to discuss his talk from the conference “Document vectors in the wild, building a content recommendation system,” in which he details how Reuters implemented document vectors to recommend content to users of their new “infinite scroll” page layout. In our conversation we take a look at what document vectors are and how they’re created, how they tested the accuracy of their models, and the future of embeddings for natural language processing.

Thanks to our Sponsors!

Thanks to Cloudera and Capital One for their continued support of the podcast and their sponsorship of this series.

Cloudera’s modern platform for machine learning and analytics, optimized for the cloud, lets you build and deploy AI solutions at scale, efficiently and securely, anywhere you want. In addition, Cloudera Fast Forward Lab’s expert guidance helps you realize your AI future, faster. To learn more, visit Cloudera’s Machine Learning resource center at cloudera.com/ml.

At the NIPS Conference in Montreal this December, researchers from Capital One will be co-hosting a workshop focused on Challenges and Opportunities for AI in Financial Services and the Impact of Fairness, Explainability, Accuracy, and Privacy. A call for papers is open now through October 25, for more information or submissions, visit twimlai.com/c1nips. A limited number of full NIPS Conference tickets are also available for accepted speakers (one full-price ticket only, applied directly to the accepted speaker),and will be made available along with author notifications on Oct 29, 2018.

About James

Mentioned in the Interview

“More On That Later” by Lee Rosevere licensed under CC By 4.0

Leave a Reply

Your email address will not be published.