Actions

Difference between revisions of "Events"

Computational Linguistics and Information Processing

m (revert.)
 
(85 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 online 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:aiwei@umiacs.umd.edu Wei Ai], the current organizer.
|id=lqah25nfftkqi2msv25trab8pk@group.calendar.google.com
 
|color=B1440E
 
|title=Upcoming Talks
 
|view=AGENDA
 
|height=300
 
}}
 
  
__NOTOC__
+
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.)
  
 +
=== Colloquium Recordings ===
 +
* [[Colloqium Recording (Fall 2020)|Fall 2020]]
 +
* [[Colloqium Recording (Spring 2021)|Spring 2021]]
  
 +
=== 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]]
  
 +
== CLIP NEWS  ==
  
 
+
* News about CLIP researchers on the UMIACS website [http://www.umiacs.umd.edu/about-us/news]
== 10/17/2012: Using Syntactic Head Information in Hierarchical Phrase-Based Translation ==
+
* Please follow us on Twitter @ClipUmd[https://twitter.com/ClipUmd?lang=en]
 
 
'''Speaker:''' Junhui Li<br/>
 
'''Time:''' Wednesday, October 17, 2012, 11:00 AM<br/>
 
'''Venue:''' AVW 3258<br/>
 
 
 
The traditional hierarchical phrase-based (HPB) model is prone to overgeneration due to lack of linguistic knowledge: the grammar may suggest more derivations than appropriate, many of which may lead to ungrammatical translations. On the other hand, limitations of glue grammar rules in HPB model may actually prevent systems from considering some reasonable derivations. This talk presents a simple but effective translation model, called the Head-Driven HPB (HD-HPB) model, which incorporates head information in translation rules to better capture syntax-driven information in a derivation. In addition, unlike the original glue rules, the HD-HPB model allows improved reordering between any two neighboring non-terminals to explore a larger reordering search space. In experiments, we examined different head label sets to refine non-terminal X, including part-of-speech (POS) tags, coarsed POS tags, dependency labels.
 
 
 
'''About the Speaker:''' Junhui Li joined CLIP lab as a post-doc researcher from Aug 2012. He was previously a post-doc researcher in the Centre for Next Generation Localisation (CNGL), at Dublin City University from Feb 2011 to Jul 2012. Before that, he was a student at NLP Lab of Soochow University, China.
 
 
 
== 10/23/2012: Bootstrapping via Graph Propagation ==
 
 
 
'''Speaker:''' [http://www.cs.sfu.ca/~anoop/ Anoop Sarkar], Simon Fraser University <br/>
 
'''Time:''' Tuesday, October 23, 2012, 2:00 PM<br/>
 
'''Venue:''' AVW 4172<br/>
 
 
 
'''Note special time and place!!!'''
 
 
 
In natural language processing, the bootstrapping algorithm introduced
 
by David Yarowsky (15 years ago) is a discriminative unsupervised
 
learning algorithm that uses some seed rules to bootstrap a classifier
 
(this is the ordinary sense of bootstrapping which is distinct from
 
the Bootstrap in statistics). The Yarowsky algorithm works remarkably
 
well on a wide variety of NLP classification tasks such as
 
distinguishing between word senses and deciding if a noun phrase is an
 
organization, location, or person.
 
 
 
Extending previous attempts at providing an objective function
 
optimization view of Yarowsky, we show that bootstrapping a classifier
 
from a small set of seed rules can be viewed as the propagation of
 
labels between examples via features shared between them. This paper
 
introduces a novel variant of the Yarowsky algorithm based on this
 
view. It is a bootstrapping learning method which uses a graph
 
propagation algorithm with a well defined per-iteration objective
 
function that incorporates the cautious behaviour of the original
 
Yarowsky algorithm.
 
 
 
The experimental results show that our proposed bootstrapping
 
algorithm achieves state of the art performance or better on several
 
different natural language data sets, outperforming other unsupervised
 
methods such as the EM algorithm. We show that cautious learning is an
 
important principle in unsupervised learning, however we do not
 
understand it well, and we show that the Yarowsky algorithm can
 
outperform or match co-training  without any reliance on multiple
 
views.
 
 
 
'''About the Speaker:''' Anoop Sarkar is an Associate Professor at Simon Fraser University in
 
British Columbia, Canada where he co-directs the [http://natlang.cs.sfu.ca Natural Language Laboratory]. He received his Ph.D. from the
 
Department of Computer and Information Sciences at the University of
 
Pennsylvania under Prof. Aravind Joshi for his work on semi-supervised
 
statistical parsing using tree-adjoining grammars.
 
 
 
His research is focused on statistical parsing and machine translation
 
(exploiting syntax or morphology, semi-supervised learning, and domain
 
adaptation). His interests also include formal language theory and
 
stochastic grammars, in particular tree automata and tree-adjoining
 
grammars.
 
 
 
== 10/31/2012: Kilian Weinberger ==
 
 
 
== 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]]
 

Latest revision as of 21:12, 31 October 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 online 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 Wei Ai, 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 @ClipUmd[2]