Actions

Difference between revisions of "Events"

Computational Linguistics and Information Processing

(79 intermediate revisions by 8 users not shown)
Line 1: Line 1:
The CLIP Colloquium is a weekly speaker series organized and hosted by CLIP Lab. The talks are open to everyone. Most talks are held at 11AM in AV Williams 3258 unless otherwise noted. Typically, external speakers have slots for one-on-one meetings with Maryland researchers before and after the talks; contact the host if you'd like to have a meeting.
+
<center>[[Image:colloq.jpg|center|504px|x]]</center>
  
If you would like to get on the cl-colloquium@umiacs.umd.edu list or for other questions about the colloquium series, e-mail [mailto:jimmylin@umd.edu Jimmy Lin], the current organizer.
+
== CLIP Colloquium ==
  
 +
The CLIP Colloquium is a weekly speaker series organized and hosted by CLIP Lab. The talks are open to everyone. Most talks are held on Wednesday at 11AM in AV Williams 3258 unless otherwise noted. Typically, external speakers have slots for one-on-one meetings with Maryland researchers.
  
{{#widget:Google Calendar
+
If you would like to get on the clip-talks@umiacs.umd.edu list or for other questions about the colloquium series, e-mail [mailto:oard@umiacs.umd.edu Doug Oard], the current organizer.
|id=lqah25nfftkqi2msv25trab8pk@group.calendar.google.com
 
|color=B1440E
 
|title=Upcoming Talks
 
|view=AGENDA
 
|height=300
 
}}
 
__NOTOC__
 
== 12/05/2012: Combining Statistical Translation Techniques for Cross-Language Information Retrieval ==
 
  
'''Speaker:''' [http://www.cs.umd.edu/~fture/Home.html Ferhan Ture], University of Maryland<br/>
+
For up-to-date information, see the [https://talks.cs.umd.edu/lists/7 UMD CS Talks page](You can also subscribe to the calendar there.)
'''Time:''' Wednesday, December 5, 2012, 11:00 AM<br/>
 
'''Venue:''' AVW 3258<br/>
 
  
Cross-language information retrieval today is dominated by techniques
+
=== Colloquium Recordings ===
that rely principally on context-independent token-to-token mappings
+
* [[Colloqium Recording (Fall 2020)|Fall 2020]]
despite the fact that state-of-the-art statistical machine translation
+
* [[Colloqium Recording (Spring 2021)|Spring 2021]]
systems now have far richer translation models available in their
 
internal representations. This paper explores combination-of-evidence
 
techniques using three types of statistical translation models:
 
context-independent token translation, token translation using
 
phrase-dependent contexts, and token translation using
 
sentence-dependent contexts. Context-independent translation is
 
performed using statistically-aligned tokens in parallel text,
 
phrase-dependent translation is performed using aligned statistical
 
phrases, and sentence-dependent translation is performed using those
 
same aligned phrases together with an $n$-gram language model.
 
Experiments on retrieval of Arabic, Chinese, and French documents
 
using English queries show that no one technique is optimal for all
 
queries, but that statistically significant improvements in mean
 
average precision over strong baselines can be achieved by combining
 
translation evidence from all three techniques. The optimal
 
combination is, however, found to be resource-dependent, indicating
 
a need for future work on robust tuning to the characteristics of
 
individual collections.
 
  
This is a practice talk for COLING 2012.
+
=== Previous Talks ===
 +
* [[https://talks.cs.umd.edu/lists/7?range=past Past talks, 2013 - present]]
 +
* [[CLIP Colloquium (Spring 2012)|Spring 2012]]  [[CLIP Colloquium (Fall 2011)|Fall 2011]]  [[CLIP Colloquium (Spring 2011)|Spring 2011]]  [[CLIP Colloquium (Fall 2010)|Fall 2010]]
  
== 01/30/2013: Human Translation and Machine Translation ==
+
== CLIP NEWS  ==
  
'''Speaker:''' [http://homepages.inf.ed.ac.uk/pkoehn/ Philipp Koehn],  University of Edinburgh<br/>
+
* News about CLIP researchers on the UMIACS website [http://www.umiacs.umd.edu/about-us/news]
'''Time:''' Wednesday, January 30, 2013, 11:00 AM<br/>
+
* Please follow us on Twitter @umdclip [https://twitter.com/umdclip?lang=en]
'''Venue:''' AVW 3258<br/>
 
 
 
== 04/10/2013: Learning with Marginalized Corrupted Features ==
 
 
 
'''Speaker:''' [http://www.cse.wustl.edu/~kilian/ Kilian Weinberger],  Washington University in St. Louis<br/>
 
'''Time:''' Wednesday, April 10, 2013, 11:00 AM<br/>
 
'''Venue:''' AVW 3258<br/>
 
 
 
If infinite amounts of labeled data are provided, many machine learning algorithms become perfect. With finite amounts of data, regularization or priors have to be used to introduce bias into a classifier. We propose a third option: learning with marginalized corrupted features. We corrupt existing data as a means to generate infinitely many additional training samples from a slightly different data distribution -- explicitly in a way that the corruption can be marginalized out in closed form. This leads to machine learning algorithms that are fast, effective and naturally scale to very large data sets. We showcase this technology in two settings: 1. to learn text document representations from unlabeled data and 2. to perform supervised learning with closed form gradient updates for empirical risk minimization.
 
 
 
Text documents (and often images) are traditionally expressed as bag-of-words feature vectors (e.g. as tf-idf). By training linear denoisers that recover unlabeled data from partial corruption, we can learn new data-specific representations. With these, we can match the world-record accuracy on the Amazon transfer learning benchmark with a simple linear classifier. In comparison with the record holder (stacked denoising autoencoders) our approach shrinks the training time from several days to a few minutes.
 
 
 
Finally, we present a variety of loss functions and corrupting distributions, which can be applied out-of-the-box with empirical risk minimization. We show that our formulation leads to significant improvements in document classification tasks over the typically used l_p norm regularization. The new learning framework is extremely versatile, generalizes better, is more stable during test-time (towards distribution drift) and only adds a few lines of code to typical risk minimization. 
 
 
 
'''About the Speaker:''' Kilian Q. Weinberger is an Assistant Professor in the Department of Computer Science & Engineering at Washington University in St. Louis. He received his Ph.D. from the University of Pennsylvania in Machine Learning under the supervision of Lawrence Saul. Prior to this, he obtained his undergraduate degree in Mathematics and Computer Science at the University of Oxford. During his career he has won several best paper awards at ICML, CVPR and AISTATS. In 2011 he was awarded the AAAI senior program chair award and in 2012 he received the NSF CAREER award. Kilian Weinberger's research is in Machine Learning and its applications. In particular, he focuses on high dimensional data analysis, metric learning, machine learned web-search ranking, transfer- and multi-task learning as well as bio medical applications.
 
 
 
 
 
== Previous Talks ==
 
* [[CLIP Colloquium (Fall 2012)|Fall 2012]]
 
* [[CLIP Colloquium (Spring 2012)|Spring 2012]]
 
* [[CLIP Colloquium (Fall 2011)|Fall 2011]]
 
* [[CLIP Colloquium (Spring 2011)|Spring 2011]]
 
* [[CLIP Colloquium (Fall 2010)|Fall 2010]]
 

Revision as of 18:21, 6 June 2021

x

CLIP Colloquium

The CLIP Colloquium is a weekly speaker series organized and hosted by CLIP Lab. The talks are open to everyone. Most talks are held on Wednesday at 11AM in AV Williams 3258 unless otherwise noted. Typically, external speakers have slots for one-on-one meetings with Maryland researchers.

If you would like to get on the clip-talks@umiacs.umd.edu list or for other questions about the colloquium series, e-mail Doug Oard, the current organizer.

For up-to-date information, see the UMD CS Talks page. (You can also subscribe to the calendar there.)

Colloquium Recordings

Previous Talks

CLIP NEWS

  • News about CLIP researchers on the UMIACS website [1]
  • Please follow us on Twitter @umdclip [2]