Serverless adventures in the world of NLP BigData и машинное обучение
Alizishaan’s professional passions revolve around two things : using technology to solve real-world problems and sharing solutions with the community. He is currently employed as a Machine Learning Engineer with Pivotus where he works on problems in the Natural Language Processing space. Over the summer of 2017, he designed and built an offensive content detection system for a Silicon Valley company. Past industry projects include a price-prediction system for cars and a status communication system that minimized false alerts.
Outside of work, Alizishaan’s passions include mountaineering, skiing, travelling and photography.
Do you marvel at the idea of production-grade Natural Language Processing (NLP) that can scale infinitely in nearly constant time?
You will learn how to design, build and deploy a general purpose NLP application using serverless computing. The talk will also cover tricks to maximize performance.
This talk will discuss:
- The design of an NLP system for batch processing texts performing tasks like tokenization, Named Entity Recognition, Part Of Speech Tagging, text-classification, etc.
- The following constraints of working with serverless computing and approaches to work with them:
* Package size restrictions.
* Memory restrictions.
* Speed.
- An automated build and deploy strategy.
- Tips and tricks to maximize performance.
