addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwchatcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgoogleimageimagesinstagramlinklocation-pinmagnifying-glassmailminusmoremuplabelShape 3 + Rectangle 1outlookpersonplusprice-ribbonImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruseryahoo

Come hear from Richard Socher - Stanford University

  • Mar 3, 2014 · 6:30 PM
  • This location is shown only to members

SPEAKER: Richard Socher - PhD student at Stanford University

We are very excited that the sixteenth distinguished speaker in this series will be Richard Socher. Doors open at 6:30pm, talk begins at 7:00pm. Drinks and light food provided.

TITLE: Recursive Deep Learning for Natural Language Processing 

Abstract: Great progress has been made in natural language processing thanks to many different algorithms, each often specific to one application. Most learning algorithms force language into simplified representations such as bag-of-words or fixed-sized windows or require human-designed features. I will introduce two general models based on recursive neural networks that can learn linguistically plausible representations of language. These methods jointly learn compositional features and grammatical sentence structure for parsing or phrase level sentiment predictions.

Besides the state-of-the-art performance, the models capture interesting phenomena in language such as compositionality. For instance, people easily see that the "with" phrase in "eating spaghetti with a spoon" specifies a way of eating whereas in "eating spaghetti with some pesto" it specifies the dish.

I show that my model solves these prepositional attachment problems well thanks to its distributed representations. In sentiment analysis, a new tensor-based recursive model learns different types of high level negation and how they can change the meaning of longer phrases with many positive words. They also learn that when contrastive conjunctions such as "but" are used the sentiment of the phrases following them usually dominates.  

Bio: Richard Socher is a PhD student at Stanford working with Chris Manning and Andrew Ng. His research interests are machine learning for natural language processing and  vision. He is interested in developing new deep learning models that  learn useful features, capture compositional structure in multiple modalities and perform well across different tasks. 

He was awarded the 2011 Yahoo! Key Scientific Challenges Award, the Distinguished Application Paper Award at ICML 2011, a Microsoft Research PhD Fellowship in 2012 and a 2013 "Magic Grant" from the Brown Institute for Media Innovation. 

Join or login to comment.

  • Sammy L.

    I haven't seen a link posted for the recording. If it's been posted, could someone forward that to me?


    April 2, 2014

  • Stephen

    Awesome talk!

    March 4, 2014

  • Emre

    Highly informative, and cutting edge; just my thing! I'd be fine with more maths, too, if it would help.

    March 4, 2014

  • Jennifer H.

    This was a great talk! Thank you Richard for speaking and thank you Adobe for hosting!

    March 4, 2014

  • Rajeev S.

    Excellent !

    March 3, 2014

  • Alex K.

    Hi, is there a video streaming for today's meetup? Thanks!

    March 3, 2014

  • Vijay B.

    Sorry, turns out I cannot join. I look forward to the recording !

    March 3, 2014

  • Ashish M.

    Interested in anything ML

    February 28, 2014

  • A former member
    A former member

    I'd love to be there but I'll be out of town - any chance it'll be recorded? Thanks!

    February 25, 2014

    • Tom J.

      Yes, the event will be recorded with the link posted here afterwards.

      1 · February 26, 2014

    • A former member
      A former member

      fabulous - thank you.

      February 26, 2014

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy