[Colloquium] Reminder: Ding/MS Presentation/Jun 13, 2019

[Margaret Jaffey]

This is a reminder about Xiaoan Ding's MS Presentation tomorrow.

------------------------------------------------------------------------------
Date:  Thursday, June 13, 2019

Time:  10:00 AM

Place:  John Crerar Library 298

M.S. Candidate:  Xiaoan Ding

M.S. Paper Title: Latent-Variable Generative Text Classifiers for
Data-Efficient NLP

Abstract:
Generative classifiers offer potential advantages over their
discriminative counterparts, namely in the areas of data efficiency,
robustness to data shift and adversarial examples, and zero-shot
learning (Ng and Jordan, 2002; Yogatama et al., 2017; Lewis and Fan,
2018). In this paper, we improve generative text classifiers by
introducing discrete latent variables into the generative story, and
explore several graphical model configurations. We parameterize the
distributions using standard neural architectures used in conditional
language modeling and perform learning by directly maximizing the log
marginal likelihood via gradient-based optimization, which avoids the
need to do expectation-maximization. We empirically characterize the
performance of our models on six text classification datasets. The
choice of where to include the latent variable has a significant
impact on performance, with the strongest results obtained when using
the latent variable as an auxiliary conditioning variable in the
generation of the textual input. This model consistently outperforms
both the generative and discriminative classifiers in data-efficient
settings.

Xiaoan's advisors are Prof. Janos Simon and Prof. Kevin Gimpel

Login to the Computer Science Department website for details:
 https://newtraell.cs.uchicago.edu/phd/ms_announcements#xiaoanding

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Margaret P. Jaffey            margaret at cs.uchicago.edu
Department of Computer Science
Student Support Rep (Ry 156)               (773) 702-6011
The University of Chicago      http://www.cs.uchicago.edu
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=