Max-Planck-Institut für Informatik
max planck institut
mpii logo Minerva of the Max Planck Society

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Rigor in Deep Learning for NLP and IR
Speaker:Jimmy Lin
coming from:U Waterloo
Speakers Bio:Professor Jimmy Lin holds the David R. Cheriton Chair in the David R. Cheriton School of Computer Science at the University of Waterloo. Lin's research aims to build tools that help users make sense of large amounts of data. His work mostly lies at the intersection of information retrieval and natural language processing, with a focus on data-driven approaches and infrastructure issues. Although most of Lin's work deals with text, he's also worked on relational data, semi-structured data, log data, speech, and graphs. From 2010-2012, Lin spent an extended sabbatical at Twitter, where he worked on services designed to connect users with relevant content and analytics infrastructure to support data science. He currently serves as the Chief Scientist of, a Waterloo-based startup that aims to build deep natural language understanding technologies to facilitate seamless dialogues between users and systems. Experience in academia and industry guides him in building useful applications that solve real-world user problems while addressing fundamental challenges in computer science and information science. A few years ago, Lin realized that big data wasn't cool anymore, so he switched to deep learning (just like everyone else these days).
Event Type:Colloquium Lecture
Visibility:D1, D2, D3, INET, D4, D5, SWS, RG1, MMCI
We use this to send out email in the morning.
Level:Public Audience
Date, Time and Location
Date:Friday, 12 April 2019
Duration:60 Minutes
Building:E1 4
Deep learning for tackling NLP and IR problems shares many common characteristics with alchemy and astrology from centuries past: both scientists and practitioners often don't know what they're doing. The "state of the art" today is full of folklore, secret tricks, superstitions, mysterious incantations, and other black magic that's necessary to "coax" a neural network into behaving. I'm not the only one who feels this way: I'll begin with overviews of recent discussions in the community along these lines, followed by my own experiences (vicariously through students) trying to gain a rigorous understanding of what is going on. My approach and philosophy can be captured thusly, to corrupt a quote by Antoine de Saint-Exupery: "It seems that true understanding is attained, not when there is nothing more to add, but when there is nothing more to take away". This talk presents work in progress, so don't come seeking resolution, cathartic revelations, or answers.
Name(s):Petra Schaaf
EMail:--email address not disclosed on the web
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Attachments, File(s):
Petra Schaaf/MPI-INF, 04/11/2019 01:57 PM
Last modified:
Uwe Brahm/MPII/DE, 04/12/2019 07:01 AM
  • Petra Schaaf, 04/11/2019 02:00 PM -- Created document.