Actions

Events: Difference between revisions

Computational Linguistics and Information Processing

 
(225 intermediate revisions by 10 users not shown)
Line 1: Line 1:
== Colloquia ==
<center>[[Image:colloq.jpg|center|504px|x]]</center>


{{#widget:Google Calendar
== CLIP Colloquium ==
|id=j68vmmdfnnq8khdrd9f93djv84@group.calendar.google.com
|color=B1440E
|title=CLIP Events
}}


=== Past Speakers ===
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.


* Roger Levy
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:rudinger@umd.edu Rachel Rudinger], the current organizer.


=== September 22: Earl Wagner ===
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.)


'''Presenting the Context of News Events with Brussell'''
=== Colloquium Recordings ===
* [[Colloqium Recording (Fall 2020)|Fall 2020]]
* [[Colloqium Recording (Spring 2021)|Spring 2021]]
* [[Colloqium Recording (Fall 2021)|Fall 2021]]
* [[Colloqium Recording (Spring 2022)|Spring 2022]]


Using content-specific models to guide information retrieval and extraction can provide richer interfaces to end-users for both understanding the context of news events and navigating related news articles. A system, Brussell, is presented that uses semantic models to organize retrieval and extraction results, generating both storylines explaining how news event situations unfold and also biographical sketches of the situation participants. A survey of business news suggests the broad prevalence of news event situations indicating Brussell's potential utility, and its performance in finding kidnapping situations is characterized.
=== 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]]


Earl J. Wagner is a Postdoctoral Research Associate at the University of Maryland, College Park. He works with Jimmy Lin and Doug Oard on software to help users find documents relevant to their tasks. In particular, he is contributing to Ivory, a toolkit for information retrieval running on Apache's Hadoop, an open-source, Map/Reduce-based framework for cloud computing.  He previously worked with Bank of America, as a Research Affiliate with the Center for Future Banking at the MIT Media Lab where he applied MIT's common sense computing technologies to text analysis tasks in banking.  In December 2009, he completed a Ph.D. in Computer Science at Northwestern University for his work designing and developing Brussell, an intelligent news-situation analysis and presentation tool. Before joining Northwestern, Earl earned an M.S. degree at the MIT Media Lab for his work on Woodstein, a prototype tool for consumers to diagnose problems with e-commerce transactions. He earned his bachelor's degree at University of California, Berkeley studying computer science and philosophy. He has presented and published his work on Brussell and Woodstein in several conferences and workshops, including the Intelligent User Interfaces conference and the AAAI Spring Symposium. He has also spoken about this work at corporations such as IBM, Intel, Microsoft and Mastercard and universities including MIT, NYU, and Berkeley.
== CLIP NEWS  ==


=== September 29: Eugene Charniak ===
* News about CLIP researchers on the UMIACS website [http://www.umiacs.umd.edu/about-us/news]
 
* Please follow us on Twitter @ClipUmd[https://twitter.com/ClipUmd?lang=en]
'''Top-Down Nearly-Context-Sensitive Parsing'''
 
We present a new syntactic parser that works left-to-right and top
down, thus maintaining a fully-connected parse tree for a few
alternative parse hypotheses.  All of the commonly used statistical
parsers use context-free dynamic programming algorithms and as such
work bottom up on the entire sentence. Thus they only find a complete
fully connected parse at the very end.  In contrast, both subjective
and experimental evidence show that people understand a sentence
word-to-word as they go along, or close to it. The constraint that
the parser keeps one or more fully connected syntactic trees is
intended to operationalize this cognitive fact. Our parser achieves a
new best result for top-down parsers of 89.4%,a 20% error reduction
over the previous single-parser best result for parsers of this type
of 86.8% (Roark01). The improved performance is due to embracing the
very large feature set available in exchange for giving up dynamic
programming.
 
 
Eugene Charniak is University Professor of Computer Science and
Cognitive Science at Brown University and past chair of the Department
of Computer Science.  He received his A.B. degree in Physics from
University of Chicago, and a Ph.D. from M.I.T. in Computer Science.
He has published four books the most recent being Statistical Language
Learning.  He is a Fellow of the American Association of Artificial
Intelligence and was previously a Councilor of the organization.  His
research has always been in the area of language understanding or
technologies which relate to it.  Over the last 20 years years he has
been interested in statistical techniques for many areas of language
processing including parsing and discourse.
 
=== October 4: Dave Newman ===
 
'''Topic modeling: Are we there yet?'''
 
Topic models -- such as Latent Dirichlet Allocation (LDA) -- have been
heralded by many as a revolutionary method for extracting semantic
content from document collections.  The machine learning community has
been busy extending the original LDA model in dozens of ways, but this
creation of new models has far outpaced broader applications of topic
modeling. Why this gap? I will share some insights as to why topic
models are not quite ready for prime time, including results from
studies of end-users using topics to find and access online resources.
I will present a pointwise mutual information (PMI) based measure that
is useful for evaluating topic models, as an alternative to perplexity
or log-likelihood of test data.  I will then show how one can leverage
PMI data to structure Dirichlet priors which regularize the learning
of topic models -- particularly for small or noisy document
collections -- to learn topics that are more coherent and
interpretable.
 
David Newman is a Research Scientist in the Department of
Computer Science at the University of California, Irvine and currently
visiting NICTA Australia.  His research focuses on theory and
application of topic models and related text mining and machine
learning techniques.  Newman's work combines theoretical advances with
practical applications to improve the way people find and discover
information.  Newman received his PhD from Princeton University.
 
=== October 6: EMNLP Practice Talks ===
 
Some subset of:
* Jordan Boyd-Graber
* Eric Hardisty
* Hendra Setiawan
* Amit Goyal

Latest revision as of 18:22, 3 November 2023

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 Rachel Rudinger, 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]