[Theory] 12/16 TTIC Colloquium: Graham Neubig, Carnegie Mellon University

[Mary Marre]

*When:*      Monday, December 16th at 11:00 am



*Where:*     TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526



*Who: *       Graham Neubig, Carnegie Mellon University


*Title:* Learning about Language with Normalizing Flows

*Abstract: *Human language is complex and highly structured, with the
unique syntax of each language defining this structure. While analyzing
this structure and using it to train better NLP models is of inherent
interest to linguists and NLP practitioners, for most languages in the
world there is a paucity of labeled data. In this talk, I will discuss
methods for learning about this structure and the correspondence between
languages, specifically take advantage of a powerful tool called
normalizing flows to build generative models over complex underlying
structures. First, I will give a brief overview of normalizing flows, using
an example from our recent work that uses these techniques to learn
bilingual word embeddings. Then, I will demonstrate how these can be
applied to learning for part-of-speech tagging, dependency parsing, or
machine translation.

*References:*
* Variational Inference with Normalizing Flows (
https://arxiv.org/pdf/1505.05770)
* Density Matching for Bilingual Word Embedding (
https://arxiv.org/abs/1904.02343)
* Unsupervised Learning of Syntactic Structure with Invertible Neural
Projections (https://arxiv.org/abs/1808.09111)
* Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of
Invertible Projections (https://arxiv.org/abs/1906.02656)
* FlowSeq: Non-Autoregressive Conditional Sequence Generation with
Generative Flow (https://arxiv.org/abs/1909.02480)

*Bio:*
Graham Neubig is an assistant professor at the Language Technologies
Institute of Carnegie Mellon University. His work focuses on natural
language processing, specifically multi-lingual models that work in many
different languages, and natural language interfaces that allow humans to
communicate with computers in their own language. Much of this work relies
on machine learning to create these systems from data, and he is also
active in developing methods and algorithms for machine learning over
natural language data. He publishes regularly in the top venues in natural
language processing, machine learning, and speech, and his work
occasionally wins awards such as best papers at EMNLP, EACL, and WNMT. He
is also active in developing open-source software, and is the main
developer of the DyNet neural network toolkit.

*Host:* Kevin Gimpel <kgimpel at ttic.edu>

For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20191209/4f88cc60/attachment.html>