[Colloquium] REMINDER: ​9/30 Distinguished Lecture Series: Sanjeev Arora, Princeton University

[Mary Marre]

*Distinguished Lecture Series: Sanjeev Arora, Princeton University*

 [image: Inline image 1]



*Wednesday, September 30, 2015 at 11:00 am*

*TTI**C*

*6045 S. Kenwood Avenue*
*Room #526​*

*Sanjeev Arora, PhD*; Charles C. Fitzmorris Professor of Computer Science,
Princeton University.


*Homepage <https://www.cs.princeton.edu/~arora/>*


*Title:* Random Walks on Discourse Spaces: a Generative Model Approach to
Semantic Word Embeddings


*Abstract:* Semantic word embeddings represent words as vectors in a
geometric space. They are useful for many NLP tasks and often constructed
using nonlinear/nonconvex techniques such as deep nets and energy-based
models. Recently Mikolov et al (2013) showed that such embeddings exhibit
linear structure that can be used to solve "word analogy tasks" such as
man: woman :: king: ??.  Subsequently, Levy and Goldberg (2014) and
Pennington et al (2014) tried to explain why such linear structure should
arise in embeddings derived from nonlinear methods. We point out gaps in
these explanations and provide a more complete explanation in the form of a
loglinear generative model for text corpora that directly models latent
semantic structure in words and involves random walk in the context space.
A rigorous mathematical analysis is performed to obtain explicit
expressions for word co-occurrence probabilities, which leads to a
surprising explanation for why low-dimensional word embeddings exist and
why they exhibit linear structure that allows solving analogies. It also
casts new light on older "Vector Space methods." Our model and its analysis
leads to several counterintuitive predictions, which are also empirically
verified.We think our methodology and generative model may be useful for
other NLP tasks.



Joint work with Yuanzhi Li, Yingyu Liang, Tengyu Ma, and Andrej Risteski
(listed in alphabetical order).



*Bio:* Sanjeev Arora is Charles C. Fitzmorris Professor of Computer Science
at Princeton University. His research area spans several areas of
theoretical Computer Science including computational complexity and
algorithm design, and theoretical problems in machine learning. He has
received the ACM-EATCS Gödel Prize (in 2001 and 2010), Packard Fellowship
(1997), the ACM Infosys Foundation Award in the Computing Sciences (2012),
the Fulkerson Prize (2012), and the Simons Investigator Award (2012)





Hosted: Julia Chuzhoy, cjulia at ttic.edu








Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757 <%28773%29%20834-1757>*
*f: (773) 357-6970 <%28773%29%20357-6970>*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20150929/091c4857/attachment-0001.htm 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 68783 bytes
Desc: not available
Url : http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20150929/091c4857/attachment-0001.png 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Distinguished Lecture Series poster 2015-16.pdf
Type: application/pdf
Size: 98661 bytes
Desc: not available
Url : http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20150929/091c4857/attachment-0001.pdf