NLP at Scale

At this talk, we will discuss the system-centric approach to the NLP. There was huge progress in NLP modeling based on transformer-based neural architectures.

We will discuss how to build a large-scale NLP system supporting high loads by the number of queries per second or amounts of documents to be processed, a large number of models, a large number of scientists working in parallel.

We will talk about multiple different approaches to build production scale NLP systems and we will discuss different tradeoffs in building such systems.

About the speaker

Andrei Lopatenko

VP Engineering at Zillow

As Vice President of Engineering at Zillow Group, Andrei leads the teams responsible for the company’s search and discovery engines, including search science, development, infrastructure, and operations.

As part of this role, he heads Zillow Group’s conversational AI and NLP efforts, which consist of initiatives around natural language processing platforms, speech analytics, call center AI, and conversational interfaces, which improve Zillow’s business and customer services using natural language processing and speech understanding. Before joining Zillow in 2019, Andrei led search science teams within eBay and Walmart.

Prior to Walmart he worked at Google and Apple, serving as a core contributor to products like Google web search, Apple Maps, Apple’s AppStore, and iTunes search engines. He previously led engineering efforts for Recruit Holdings’ AI Lab.

He was a co-founder and sat on the advisory board of Ozlo, a Conversational AI startup acquired by Facebook in 2017. Andrei earned a Doctor of Philosophy in Computer Science from The University of Manchester, United Kingdom, and a Master of Science Degree from the Moscow Institute of Physics and Technology.



Sessions: October 5 – 7
Trainings: October 8 – 9


Presented by