Difference between revisions of "NAACL SSL-NLP 2009"

From Openresearch
Jump to: navigation, search
(Event created)
 
(Event created)
 
(2 intermediate revisions by the same user not shown)
Line 3: Line 3:
 
  | Title = Workshop on Semi-supervised Learning for Natural Language Processing at NAACL HLT 2009
 
  | Title = Workshop on Semi-supervised Learning for Natural Language Processing at NAACL HLT 2009
 
  | Type = Conference
 
  | Type = Conference
−
  | Field = Parallel computing
+
  | Field = Machine learning
−
  | Homepage = www.cluster2009.org/
+
  | Homepage = sites.google.com/site/sslnlp/
−
  | Start date = Aug 29, 2009  
+
  | Start date = Jun 4, 2009  
−
  | End date =  Sep 4, 2009
+
  | End date =  Jun 5, 2009
−
  | City= New Orleans
+
  | City= Boulder
−
  | State =  Louisiana
+
  | State =  Colorado
 
  | Country =  USA
 
  | Country =  USA
−
  | Abstract deadline = Apr 14, 2009
+
  | Abstract deadline =  
−
  | Submission deadline = Apr 14, 2009
+
  | Submission deadline = Mar 6, 2009
−
  | Notification = Jun 5, 2009
+
  | Notification = Mar 30, 2009
−
  | Camera ready = Jul 31, 2009
+
  | Camera ready = Apr 12, 2009
 
}}
 
}}
  
 +
<pre>
 +
NAACL HLT 2009 Workshop on
 +
Semi-supervised Learning for Natural Language Processing
  
−
*********************************************************************
+
June 4 or 5, 2009, Boulder, Colorado, USA
 +
http://sites.google.com/site/sslnlp/
  
−
                        Call for Papers
+
Call for Papers
 +
(Submission deadline: March 6, 2009)
 +
================================================
  
−
    2009 IEEE International Conference on Cluster Computing
+
Machine learning, be it supervised or unsupervised, has become an indispensable tool for natural language processing (NLP) researchers. Highly developed supervised training techniques have led to state-of-the-art performance for many NLP tasks and provide foundations for deployable NLP systems. Similarly, unsupervised methods, such as those based on EM training, have also been influential, with applications ranging from grammar induction to bilingual word alignment for machine translation.
−
                        (Cluster 2009)
 
  
−
                http://www.cluster2009.org/
+
Unfortunately, given the limited availability of annotated data, and the non-trivial cost of obtaining additional annotated data, progress on supervised learning often yields diminishing returns. Unsupervised learning, on the other hand, is not bound by the same data resource limits. However, unsupervised learning is significantly harder than supervised learning and, although intriguing, has not been able to produce consistently successful results for complex structured prediction problems characteristic of NLP.
  
−
                  29 August - 4 September 2009
+
It is becoming increasingly important to leverage both types of data resources, labeled and unlabeled, to achieve the best performance in challenging NLP problems. Consequently, interest in semi-supervised learning has grown in the NLP community in recent years. Yet, although several papers have demonstrated promising results with semi-supervised learning for problems such as tagging and parsing, we suspect that good results might not be easy to achieve across the board. Many semi-supervised learning methods (e.g. transductive SVM, graph-based methods) have been originally developed for binary classification problems. NLP problems often pose new challenges to these techniques, involving more complex structure that can violate many of the underlying assumptions.
  
−
                  New Orleans, Louisiana, USA
+
We believe there is a need to take a step back and investigate why and how auxiliary unlabeled data can truly improve training for NLP tasks.
  
−
**********************************************************************
+
In particular, many open questions remain:
  
−
Cluster 2009 welcomes paper and poster submissions on innovative work from
+
1. Problem Structure: What are the different classes of NLP problem structures (e.g. sequences, trees, N-best lists) and what algorithms are best suited for each class? For instance, can graph-based algorithms be successfully applied to sequence-to-sequence problems like machine translation, or are self-training and feature-based methods the only reasonable choices for these problems?
−
researchers in academia, industry, and government, describing original research
 
−
in the field of cluster computing. Topics of interest include, but are not
 
−
limited to:
 
  
−
• Cluster Architecture and Hardware Systems
+
2. Background Knowledge: What kinds of NLP-specific background knowledge can we exploit to aid semi-supervised learning? Recent learning paradigms such as constraint-driven learning and prototype learning take advantage of our domain knowledge about particular NLP tasks; they represent a move away from purely data-agnostic methods and are good examples of how linguistic intuition can drive algorithm development.
−
◦ Node architectures
 
−
◦ Packaging, Power, and Cooling
 
−
• Cluster Software and Middleware
 
−
◦ Software Environments and Tools
 
−
◦ Single -System Image Services
 
−
◦ Parallel File Systems and I/O Libraries
 
−
◦ Standard Software for Clusters
 
−
◦ Virtualization
 
−
• Cluster Networking
 
−
◦ High-Speed Interconnects
 
−
◦ High Performance Message Passing Libraries
 
−
◦ Lightweight Communication Protocols
 
−
• Implications of Multicore and Clouds on Clusters
 
−
◦ Hardware Architecture
 
−
◦ Software and Tools
 
−
◦ Networking
 
−
◦ Management
 
−
◦ Applications
 
−
• Applications
 
−
◦ Application Methods and Algorithms
 
−
◦ Adaptation to Multicore
 
−
◦ Data Distribution, Load Balancing & Scaling
 
−
◦ MPI/OpenMP Hybrid Computing
 
−
◦ Visualization
 
−
• Performance Analysis and Evaluation
 
−
◦ Benchmarking & Profiling Tools
 
−
◦ Performance Prediction & Modeling
 
−
• Cluster Management
 
−
◦ Security and Reliability
 
−
◦ High Availability Solutions
 
−
◦ Resource and Job Management
 
  
−
For submitting and formatting instructions, see the conference
+
3. Scalability: NLP data-sets are often large. What are the scalability challenges and solutions for applying existing semi-supervised learning algorithms to NLP data?
−
web site: http://www.cluster2009.org/
 
  
−
Important Dates:
+
4. Evaluation and Negative Results: What can we learn from negative results? Can we make an educated guess as to when semi-supervised learning might outperform supervised or unsupervised learning based on what we know about the NLP problem?
  
−
  Workshop proposal deadline: 26 November 2008
+
5. To Use or Not To Use: Should semi-supervised learning only be employed in low-resource languages/tasks (i.e. little labeled data, much unlabeled data), or should we expect gains even in high-resource scenarios (i.e. expecting semi-supervised learning to improve on a supervised system that is already more than 95% accurate)?
−
  Workshop notification: 22 December 2008
 
−
  Tutorial proposal deadline: 31 March 2009
 
−
  Technical paper submissions: 14 April 2009
 
−
  Tutorial notification: 31 May 2009
 
−
  Technical paper notification: 5 June 2009
 
−
  Poster submissions: 12 June 2009
 
−
  Poster notification: 17 July 2009
 
−
  Poster camera ready deadline: 31 July 2009
 
−
  Paper camera ready deadline: 31 July 2009
 
  
−
Conference Organizing Chairs and Committees:
+
This workshop aims to bring together researchers dedicated to making semi-supervised learning work for NLP problems. Our goal is to help build a community of researchers and foster deep discussions about insights, speculations, and results (both positive and negative) that may otherwise not appear in a technical paper at a major conference. We welcome submissions that address any of the above questions or other relevant issues, and especially encourage authors to provide a deep analysis of data and results. Papers will be limited to 8 pages and will be selected based on quality and relevance to workshop goals.
  
−
General Chair
+
IMPORTANT DATES:
−
  Daniel S. Katz, Louisiana State University, USA
+
March 6, 2009: Submission deadline
−
General Vice Chair
+
March 30, 2009: Notification of acceptance
−
  Mark Baker, University of Reading, UK
+
April 12, 2009: Camera-ready copies due
−
Program Chair
+
June 4 or 5, 2009: Workshop held in conjunction with NAACL HLT (exact date to be announced)
−
  Thomas Sterling, Louisiana State University, USA
+
 
−
Program Vice Chairs
+
PROGRAM COMMITTEE:
−
  Pete Beckman, Argonne National Lab, USA
+
Steven Abney (University of Michigan, USA)
−
  William Camp, Intel, USA
+
Yasemin Altun (Max Planck Institute for Biological Cybernetics, Germany)
−
  Jack Dongarra, University of Tennessee at Knoxville, USA
+
Tim Baldwin (University of Melbourne, Australia)
−
  William Gropp, University of Illinois, USA
+
Shane Bergsma (University of Alberta, Canada)
−
  Satoshi Matsuoka, Tokyo Institute of Technology, Japan
+
Antal van den Bosch (Tilburg University, The Netherlands)
−
  Bart Miller, Univ. of Wisconsin, USA
+
John Blitzer (UC Berkeley, USA)
−
Poster Co-Chairs
+
Ming-Wei Chang (UIUC, USA)
−
  Sushil Prasad, Georgia State University, USA
+
Walter Daelemans (University of Antwerp, Belgium)
−
  Eric Aubanel, University of New Brunswick, Canada
+
Hal Daume III (University of Utah, USA)
−
Workshops Chair
+
Kevin Gimpel (Carnegie Mellon University, USA)
−
  Wu Feng, Virginia Tech, USA
+
Andrew Goldberg (University of Wisconsin, USA)
−
Tutorials Co-Chairs
+
Liang Huang (Google Research, USA)
−
  Robert Ferraro, Jet Propulsion Laboratory, USA
+
Rie Johnson [formerly, Ando] (RJ Research Consulting)
−
  Bryan Biegel, NASA Ames, USA
+
Katrin Kirchhoff (University of Washington, USA)
−
Proceedings Chair
+
Percy Liang (UC Berkeley, USA)
−
  Ron Brightwell, Sandia National Laboratories, USA
+
Gary Geunbae Lee (POSTECH, Korea)
−
Publicity Co-Chairs
+
Gina-Anne Levow (University of Chicago, USA)
−
  Omer Rana, Cardiff University, UK
+
Gideon Mann (Google, USA)
−
  Feilong Tang, Shanghai Jiao Tong University, China
+
David McClotsky (Brown University, USA)
−
  Tevfik Kosar, Louisiana State University, USA
+
Ray Mooney (UT Austin, USA)
−
Finance Chair
+
Hwee Tou Ng (National University of Singapore, Singapore)
−
  Box Leangsuksun, Louisiana Tech University, USA
+
Vincent Ng (UT Dallas, USA)
−
Sponsor and Exhibitors Co-Chairs
+
Miles Osborne (University of Edinburgh, UK)
−
  George Jones, Data Direct Networks, USA
+
Mari Ostendorf (University of Washington, USA)
−
  Charlie McMahon, Louisiana State University, USA
+
Chris Pinchak (University of Alberta, Canada)
−
Local Arrangements Chair
+
Dragomir Radev (University of Michigan, USA)
−
  Karen Jones, Louisiana State University, USA
+
Dan Roth (UIUC, USA)
−
PR/Graphics Chair
+
Anoop Sarkar (Simon Fraser University, Canada)
−
  Kristen Sunde, Louisiana State University, USA
+
Dale Schuurmans (University of Alberta, Canada)
 +
Akira Shimazu (JAIST, Japan)
 +
Jun Suzuki (NTT, Japan)
 +
Yee Whye Teh (University College London, UK)
 +
Kristina Toutanova (Microsoft Research, USA)
 +
Jason Weston (NEC, USA)
 +
Tong Zhang (Rutgers University, USA)
 +
Ming Zhou (Microsoft Research Asia, China)
 +
Xiaojin (Jerry) Zhu (University of Wisconsin, USA)
 +
 
 +
ORGANIZERS AND CONTACT:
 +
- Qin Wang (Yahoo!)
 +
- Kevin Duh (University of Washington)
 +
- Dekang Lin (Google Research)
 +
Email: ssl.nlp2009@gmail.com
 +
Website: http://sites.google.com/site/sslnlp/
 +
</pre>This CfP was obtained from [http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=3866&amp;copyownerid=2077 WikiCFP][[Category:Natural language processing]]

Latest revision as of 05:50, 14 October 2008

NAACL SSL-NLP 2009
Workshop on Semi-supervised Learning for Natural Language Processing at NAACL HLT 2009
Dates Jun 4, 2009 (iCal) - Jun 5, 2009
Homepage: sites.google.com/site/sslnlp/
Location
Location: Boulder, Colorado, USA
Loading map...

Important dates
Submissions: Mar 6, 2009
Notification: Mar 30, 2009
Camera ready due: Apr 12, 2009
Table of Contents 


NAACL HLT 2009 Workshop on
Semi-supervised Learning for Natural Language Processing

June 4 or 5, 2009, Boulder, Colorado, USA
http://sites.google.com/site/sslnlp/

Call for Papers
(Submission deadline: March 6, 2009)
================================================

Machine learning, be it supervised or unsupervised, has become an indispensable tool for natural language processing (NLP) researchers. Highly developed supervised training techniques have led to state-of-the-art performance for many NLP tasks and provide foundations for deployable NLP systems. Similarly, unsupervised methods, such as those based on EM training, have also been influential, with applications ranging from grammar induction to bilingual word alignment for machine translation.

Unfortunately, given the limited availability of annotated data, and the non-trivial cost of obtaining additional annotated data, progress on supervised learning often yields diminishing returns. Unsupervised learning, on the other hand, is not bound by the same data resource limits. However, unsupervised learning is significantly harder than supervised learning and, although intriguing, has not been able to produce consistently successful results for complex structured prediction problems characteristic of NLP.

It is becoming increasingly important to leverage both types of data resources, labeled and unlabeled, to achieve the best performance in challenging NLP problems. Consequently, interest in semi-supervised learning has grown in the NLP community in recent years. Yet, although several papers have demonstrated promising results with semi-supervised learning for problems such as tagging and parsing, we suspect that good results might not be easy to achieve across the board. Many semi-supervised learning methods (e.g. transductive SVM, graph-based methods) have been originally developed for binary classification problems. NLP problems often pose new challenges to these techniques, involving more complex structure that can violate many of the underlying assumptions.

We believe there is a need to take a step back and investigate why and how auxiliary unlabeled data can truly improve training for NLP tasks.

In particular, many open questions remain:

1. Problem Structure: What are the different classes of NLP problem structures (e.g. sequences, trees, N-best lists) and what algorithms are best suited for each class? For instance, can graph-based algorithms be successfully applied to sequence-to-sequence problems like machine translation, or are self-training and feature-based methods the only reasonable choices for these problems?

2. Background Knowledge: What kinds of NLP-specific background knowledge can we exploit to aid semi-supervised learning? Recent learning paradigms such as constraint-driven learning and prototype learning take advantage of our domain knowledge about particular NLP tasks; they represent a move away from purely data-agnostic methods and are good examples of how linguistic intuition can drive algorithm development.

3. Scalability: NLP data-sets are often large. What are the scalability challenges and solutions for applying existing semi-supervised learning algorithms to NLP data?

4. Evaluation and Negative Results: What can we learn from negative results? Can we make an educated guess as to when semi-supervised learning might outperform supervised or unsupervised learning based on what we know about the NLP problem?

5. To Use or Not To Use: Should semi-supervised learning only be employed in low-resource languages/tasks (i.e. little labeled data, much unlabeled data), or should we expect gains even in high-resource scenarios (i.e. expecting semi-supervised learning to improve on a supervised system that is already more than 95% accurate)?

This workshop aims to bring together researchers dedicated to making semi-supervised learning work for NLP problems. Our goal is to help build a community of researchers and foster deep discussions about insights, speculations, and results (both positive and negative) that may otherwise not appear in a technical paper at a major conference. We welcome submissions that address any of the above questions or other relevant issues, and especially encourage authors to provide a deep analysis of data and results. Papers will be limited to 8 pages and will be selected based on quality and relevance to workshop goals.

IMPORTANT DATES:
March 6, 2009: Submission deadline
March 30, 2009: Notification of acceptance
April 12, 2009: Camera-ready copies due
June 4 or 5, 2009: Workshop held in conjunction with NAACL HLT (exact date to be announced)

PROGRAM COMMITTEE:
Steven Abney (University of Michigan, USA)
Yasemin Altun (Max Planck Institute for Biological Cybernetics, Germany)
Tim Baldwin (University of Melbourne, Australia)
Shane Bergsma (University of Alberta, Canada)
Antal van den Bosch (Tilburg University, The Netherlands)
John Blitzer (UC Berkeley, USA)
Ming-Wei Chang (UIUC, USA)
Walter Daelemans (University of Antwerp, Belgium)
Hal Daume III (University of Utah, USA)
Kevin Gimpel (Carnegie Mellon University, USA)
Andrew Goldberg (University of Wisconsin, USA)
Liang Huang (Google Research, USA)
Rie Johnson [formerly, Ando] (RJ Research Consulting)
Katrin Kirchhoff (University of Washington, USA)
Percy Liang (UC Berkeley, USA)
Gary Geunbae Lee (POSTECH, Korea)
Gina-Anne Levow (University of Chicago, USA)
Gideon Mann (Google, USA)
David McClotsky (Brown University, USA)
Ray Mooney (UT Austin, USA)
Hwee Tou Ng (National University of Singapore, Singapore)
Vincent Ng (UT Dallas, USA)
Miles Osborne (University of Edinburgh, UK)
Mari Ostendorf (University of Washington, USA)
Chris Pinchak (University of Alberta, Canada)
Dragomir Radev (University of Michigan, USA)
Dan Roth (UIUC, USA)
Anoop Sarkar (Simon Fraser University, Canada)
Dale Schuurmans (University of Alberta, Canada)
Akira Shimazu (JAIST, Japan)
Jun Suzuki (NTT, Japan)
Yee Whye Teh (University College London, UK)
Kristina Toutanova (Microsoft Research, USA)
Jason Weston (NEC, USA)
Tong Zhang (Rutgers University, USA)
Ming Zhou (Microsoft Research Asia, China)
Xiaojin (Jerry) Zhu (University of Wisconsin, USA)

ORGANIZERS AND CONTACT:
- Qin Wang (Yahoo!)
- Kevin Duh (University of Washington)
- Dekang Lin (Google Research)
Email: ssl.nlp2009@gmail.com
Website: http://sites.google.com/site/sslnlp/

This CfP was obtained from WikiCFP

Retrieved from "https://www.openresearch.org/mediawiki/index.php?title=NAACL_SSL-NLP_2009&oldid=5239"
Facts about "NAACL SSL-NLP 2009"
RDF feed
AcronymNAACL SSL-NLP 2009 +
Camera ready dueApril 12, 2009 +
End dateJune 5, 2009 +
Event typeConference +
Has coordinates40° 0' 54", -105° 16' 14"Latitude: 40.014986111111
Longitude: -105.27054444444 +
Has location cityBoulder +
Has location countryCategory:USA +
Has location stateColorado +
Homepagehttp://sites.google.com/site/sslnlp/ +
IsAEvent +
NotificationMarch 30, 2009 +
Start dateJune 4, 2009 +
Submission deadlineMarch 6, 2009 +
TitleWorkshop on Semi-supervised Learning for Natural Language Processing at NAACL HLT 2009 +