Actions

Events: Difference between revisions

Computational Linguistics and Information Processing

No edit summary
No edit summary
Line 13: Line 13:


__NOTOC__
__NOTOC__
== 09/05/2012: 5 Minute Madness (Part I) ==
== 09/12/2012: 5 Minute Madness (Part II) ==
== 09/19/2012: CoB: Pairwise Similarity on Large Text Collections with MapReduce==
== 09/19/2012: CoB: Pairwise Similarity on Large Text Collections with MapReduce==
'''Speaker:''' Earl Wagner, University of Maryland<br/>
'''Speaker:''' Earl Wagner, University of Maryland<br/>
'''Time:''' Wednesday, September 19, 2012, 11:00 AM<br/>
'''Venue:''' AVW 3258<br/>
== 09/26/2012: Better! Faster! Stronger (theorems)! Learning to Balance Accuracy and Efficiency when Predicting Linguistic Structures ==
'''Speaker:''' Hal Daume III, University of Maryland<br/>
'''Time:''' Wednesday, September 26, 2012, 11:00 AM<br/>
'''Time:''' Wednesday, September 26, 2012, 11:00 AM<br/>
'''Venue:''' AVW 3258<br/>
'''Venue:''' AVW 3258<br/>


== 09/26/2012: Hal Daume III ==
Viewed abstractly, many classic problems in natural language
processing can be cast as trying to map a complex input (eg., a
sequence of words) to a complex output (eg., a syntax tree or
semantic graph).  This task is challenging both because language
is ambiguous (learning difficulties) and represented with
discrete combinatorial structures (computational difficulties).
I will describe my multi-pronged research effort to develope
learning algorithms that explicitly learn to trade-off accuracy
and efficiency, applied to a variety of language processing
phenomena.  Moreover, I will show that in some cases, we can
actually obtain model that is faster and more accurate by
exploiting smarter learning algorithms.  And yes, those
algorithms come with stronger theoretical guarantees too.
 
The key insight that makes this possible is a connection between
the task of predicting structured objects (what I care about) and
imitation learning (a subfield in robotics).  This insight came
about as a result of my work a few years ago, and has formed the
backbone of much of my work since then.  These connections have
led other NLP and robotics researchers to make their own
independent advances using many of these ideas.
 
At the end of the talk, I'll briefly survey some of my other
contributions in the areas of domain adaptation and multilingual
modeling, both of which also fall under the general rubric
of "what goes wrong when I try to apply off-the-shelf machine
learning models to real language processing problems?"


== 10/03/2012: Shay Cohen ==
== 10/03/2012: Shay Cohen ==
Line 32: Line 58:
'''Venue:''' AVW 3258<br/>
'''Venue:''' AVW 3258<br/>


'''Abstract:''' The transition-based approach to dependency parsing has become
The transition-based approach to dependency parsing has become
popular thanks to its simplicity and efficiency. Systems like MaltParser
popular thanks to its simplicity and efficiency. Systems like MaltParser
achieve linear-time parsing with projective dependency trees using locally
achieve linear-time parsing with projective dependency trees using locally
Line 64: Line 90:
'''Host:''' Hal Daume III, hal@umd.edu
'''Host:''' Hal Daume III, hal@umd.edu


== 10/23/2012: Anoop Sarkar ==
== 10/23/2012: Bootstrapping via Graph Propagation ==


'''Speaker:''' [http://www.cs.sfu.ca/~anoop/ Anoop Sarkar], Simon Fraser University <br/>
'''Speaker:''' [http://www.cs.sfu.ca/~anoop/ Anoop Sarkar], Simon Fraser University <br/>
Line 71: Line 97:


'''Note special time and place!!!'''
'''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 ==
== 10/31/2012: Kilian Weinberger ==

Revision as of 18:21, 14 September 2012

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.

If you would like to get on the cl-colloquium@umiacs.umd.edu list or for other questions about the colloquium series, e-mail Jimmy Lin, the current organizer.


{{#widget:Google Calendar |id=lqah25nfftkqi2msv25trab8pk@group.calendar.google.com |color=B1440E |title=Upcoming Talks |view=AGENDA |height=300 }}


09/19/2012: CoB: Pairwise Similarity on Large Text Collections with MapReduce

Speaker: Earl Wagner, University of Maryland
Time: Wednesday, September 19, 2012, 11:00 AM
Venue: AVW 3258

09/26/2012: Better! Faster! Stronger (theorems)! Learning to Balance Accuracy and Efficiency when Predicting Linguistic Structures

Speaker: Hal Daume III, University of Maryland
Time: Wednesday, September 26, 2012, 11:00 AM
Venue: AVW 3258

Viewed abstractly, many classic problems in natural language processing can be cast as trying to map a complex input (eg., a sequence of words) to a complex output (eg., a syntax tree or semantic graph). This task is challenging both because language is ambiguous (learning difficulties) and represented with discrete combinatorial structures (computational difficulties). I will describe my multi-pronged research effort to develope learning algorithms that explicitly learn to trade-off accuracy and efficiency, applied to a variety of language processing phenomena. Moreover, I will show that in some cases, we can actually obtain model that is faster and more accurate by exploiting smarter learning algorithms. And yes, those algorithms come with stronger theoretical guarantees too.

The key insight that makes this possible is a connection between the task of predicting structured objects (what I care about) and imitation learning (a subfield in robotics). This insight came about as a result of my work a few years ago, and has formed the backbone of much of my work since then. These connections have led other NLP and robotics researchers to make their own independent advances using many of these ideas.

At the end of the talk, I'll briefly survey some of my other contributions in the areas of domain adaptation and multilingual modeling, both of which also fall under the general rubric of "what goes wrong when I try to apply off-the-shelf machine learning models to real language processing problems?"

10/03/2012: Shay Cohen

10/10/2012: Beyond MaltParser - Advances in Transition-Based Dependency Parsing

Speaker: Joakim Nivre, Uppsala University / Google
Time: Wednesday, October 10, 2012, 11:00 AM
Venue: AVW 3258

The transition-based approach to dependency parsing has become popular thanks to its simplicity and efficiency. Systems like MaltParser achieve linear-time parsing with projective dependency trees using locally trained classifiers to predict the next parsing action and greedy best-first search to retrieve the optimal parse tree, assuming that the input sentence has been morphologically disambiguated using a part-of-speech tagger. In this talk, I survey recent developments in transition-based dependency parsing that address some of the limitations of the basic transition-based approach. First, I show how globally trained classifiers and beam search can be used to mitigate error propagation and enable richer feature representations. Secondly, I discuss different methods for extending the coverage to non-projective trees, which are required for linguistic adequacy in many languages.Finally, I present a model for joint tagging and parsing that leads to improvements in both tagging and parsing accuracy as compared to the standard pipeline approach.

About the Speaker: Joakim Nivre is Professor of Computational Linguistics at Uppsala University and currently visiting scientist at Google, New York. He holds a Ph.D. in General Linguistics from the University of Gothenburg and a Ph.D. in Computer Science from Växjö University. Joakim's research focuses on data-driven methods for natural language processing, in particular for syntactic and semantic analysis. He is one of the main developers of the transition-based approach to syntactic dependency parsing, described in his 2006 book Inductive Dependency Parsing and implemented in the MaltParser system. Joakim's current research interests include the analysis of mildly non-projective dependency structures, the integration of morphological and syntactic processing for richly inflected languages, and methods for cross-framework parser evaluation. He has produced over 150 scientific publications, including 3 books, and has given nearly 70 invited talks at conferences and institutions around the world. He is the current secretary of the European Chapter of the Association for Computational Linguistics.

Host: Hal Daume III, hal@umd.edu

10/23/2012: Bootstrapping via Graph Propagation

Speaker: Anoop Sarkar, Simon Fraser University
Time: Tuesday, October 23, 2012, 2:00 PM
Venue: AVW 4172

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