You are viewing content from a past/completed QCon

Presentation: Deep Learning for Language Understanding (at Google Scale)

Track: Handling Sequential Data Like an Expert / ML Applied to Operations

Location: Cyril Magnin II

Duration: 10:35am - 10:45am

Day of week: Wednesday

Share this on:

Abstract

Written and spoken language are everywhere: customer reviews, online forums, chat applications, just to name a few. How can we use deep learning to extract meaning from these rich sources of data?

In this talk we'll take an in-depth look at the deep learning techniques for language understanding that are behind Google-scale applications like Gmail Smart Reply and Google Translate. We'll cover both the high level intuition for these techniques, and practical pointers for getting started in Tensorflow.

Speaker: Anjuli Kannan

Software Engineer @GoogleBrain

Anjuli Kannan is a senior software engineer at Google. She is a member of the Brain Team, which works to advance the field of machine intelligence through a combination of basic research, software (TensorFlow), and applications that improve people's lives. Anjuli is especially interested applications of machine learning to problems in natural language understanding. Recently she was a core member of the team that brought the Smart Reply feature to Inbox by Gmail. Launched in 2015, Smart Reply was the first Google-scale application to effectively apply recurrent neural networks in language understanding, as well as the first to leverage Google's open-source TensorFlow.

Find Anjuli Kannan at

2019 Tracks

  • Groking Timeseries & Sequential Data

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

  • Deep Learning in Practice

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