align-toparrow-leftarrow-rightbackbellblockcalendarcamerachatcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-crosscrosseditfacebookglobegoogleimagesinstagramlocation-pinmagnifying-glassmailmoremuplabelShape 3 + Rectangle 1outlookpersonplusImported LayersImported LayersImported Layersshieldstartwitteryahoo

Adversarial Evaluation for NLP Models

Amber Wilcox-O'Hearn will lead a discussion of Noah Smith's white paper on Adversarial Evaluation for Models of Natural Language:

Additionally Amber will be giving a demo of her work on Malaprop which introduces errors into a corpus as a means of adversarial evaluation. She has a great summary on her blog, and take a look at the code on github

Even better take the opportunity to run the code and bring your questions.

Join or login to comment.

  • A former member
    A former member

    great topic, great speaker

    November 7, 2013

  • amber

    How do-able is it to get a projector for tonight?

    November 6, 2013

    • Greg B.

      I'll have one ready, no problem. Looking forward to the discussion. Many questions from reading the paper.

      1 · November 6, 2013

  • Jeannette

    I'm working late tomorrow, so I may not make it until 7:15. Hopefully I won't miss all the good stuff!

    November 5, 2013

  • amber

    On the off-chance that someone has looked at the code already, I have just uploaded a new version of malaprop tonight, and it should make more sense.

    1 · October 23, 2013

11 went

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