You are viewing content from a past/completed QCon

Keynote: Modern NLP for Pre-Modern Practitioners

Location: Cyril Magnin Ballroom

Duration: 9:00am - 10:10am

Day of week: Tuesday

This keynote is now available to view on

Watch video with transcript


"Transformers"? "BERT"? "ELMo"?  What do NLP researchers actually do other than give things childish names? In this talk I'll discuss the kinds of problems NLP researchers are thinking about, explain their newest and hottest breakthroughs, and give you some ideas as to how you can incorporate these concepts and models into your work.

Speaker: Joel Grus

Senior Research Engineer @allen_ai

Joel Grus is a research engineer at the Allen Institute for Artificial Intelligence in Seattle, where he works on AllenNLP, a deep learning framework for AI researchers. He wrote the beloved O'Reilly book Data Science from Scratch and the beloved blog post "Fizz Buzz in Tensorflow". In his spare time he does stand-up comedy and makes livecoding videos. Oh, and he doesn't like notebooks.

Find Joel Grus at

2019 Tracks

  • Sequential Data: Natural Language, Time Series, and Sound

    Techniques, practices, and approaches around time series and sequential data. Expect topics including image recognition, NLP/NLU, preprocess, & crunching of related algorithms.

  • ML in Action

    Applied track demonstrating how to train, score, and handle common machine learning use cases, including heavy concentration in the space of security and fraud

  • Deep Learning in Practice

    Deep learning use cases around edge computing, deep learning for search, explainability, fairness, and perception.