Monday, December 21, 2009

NAACL-HLT 2010 Workshop on Active Learning for Natural Language Processing

==============================================================
First Call for Paper Submissions

NAACL-HLT 2010 Workshop on
Active Learning for Natural Language Processing (ALNLP)

June 5 or 6, 2010, Los Angeles, CA

http://www.active-learning.net/alnlp2010

Submission Deadline: March 1, 2010
==============================================================

Labeled training data is required to achieve state-of-the-art performance for many machine learning solutions to NLP tasks. While traditional supervised methods rely exclusively on existing labeled data to induce a model, active learning allows the learner to select unlabeled data for labeling in an effort to reduce annotation costs without sacrificing performance. Thus, active learning appears promising for NLP applications where unlabeled data is readily available (e.g., web pages, audio recordings, minority language data), but obtaining labels is cost-prohibitive.

Ample recent work has demonstrated the effectiveness of active learning over a diverse range of applications. Despite these findings, active learning has not yet been widely adopted for many ongoing large-scale corpora annotation efforts -- resulting in a dearth of real-world case studies and copious research questions. Machine learning literature has primarily focused on active learning in the context of classification, devoting less attention to issues specific to NLP including annotation user studies, incorporation of semantic information, and more complex prediction tasks (e.g. parsing, machine translation).

TOPICS

The aim of this workshop is to foster innovation and discussion that advances our understanding in these and other practical issues for active learning in NLP.

Topics of particular interest include:

-- Alternative query types : labeling features rather than instances, mixed-resolution queries for structured instances, etc.
-- Creative ways for obtaining data via active learning (e.g., online games, Mechanical Turk)
-- Managing multiple, possibly non-expert annotators (e.g., "crowdsourcing" environments)
-- Reusability : using data acquired with one active learner to train other model classes
-- Domain adaptation and active learning
-- Multi‐task active learning
-- Criteria for stopping and monitoring active learning progress
-- Active learning in coordination with semi-supervised or unsupervised learning approaches
-- Interactive active learning interfaces and other HCI issues
-- Parallelization of active learning and its computational challenges
-- Software engineering considerations for active learning and NLP
-- Theoretical analysis of active learning

We also welcome case-study papers describing the application of active learning in real-world annotation projects and lessons learned thereby.

Additionally, we would consider papers with insights applicable to NLP from other machine learning communities (e.g., computer vision, bioinformatics, and data mining), where annotation costs are also high.

SUBMISSIONS

We invite submissions of two kinds: 1. original and unpublished work as full papers, limited to 8 pages (+1 extra page for references); 2. position or work-in-progress papers, limited to 4 pages (including references). Both kinds of papers will appear in the proceedings and presented orally. As reviewing will be double-blind, author information should not be included in the papers and self-reference should be avoided.

All submissions must be made in PDF format using the START paper

submission website:
https://www.softconf.com/naaclhlt2010/alnlp/
Submissions must follow the NAACL HLT 2010 formatting requirements:
http://naaclhlt2010.isi.edu/authors.html
Authors are strongly encouraged to use the LaTeX or Microsoft Word style files available there. Papers not conforming to these requirements are subject to rejection without review.

IMPORTANT DATES

March 1, 2010 : Paper Submission Deadline
March 30, 2010 : Notification of acceptance
June 5 or 6, 2010 : Workshop held in conjunction with NAACL-HLT

ORGANIZERS AND CONTACT

- Burr Settles, Carnegie Mellon University, USA
- Kevin Small, Tufts University, USA
- Katrin Tomanek, University of Jena, Germany

Please address any queries regarding the workshop to:
alnlp2010@gmail.com


PROGRAM COMMITTEE

- Markus Becker (SPSS, UK)
- Claire Cardie (Cornell University, USA)
- Hal Daume III (University of Utah, USA)
- Ben Hachey (University of Edinburgh, UK)
- Robbie Haertel (Brigham Young University, USA)
- Udo Hahn (University of Jena, Germany)
- Eric Horvitz (Microsoft Research, USA)
- Rebecca Hwa (University of Pittsburgh, USA)
- Ashish Kapoor (Microsoft Research, USA)
- Prem Melville (IBM T.J. Watson Research Center, USA)
- Ray Mooney (University of Texas at Austin, USA)
- Fredrik Olsson (SICS, Sweden)
- Foster Provost (New York University, USA)
- Eric Ringger (Brigham Young University, USA)
- Dan Roth (University of Illinois at Urbana-Champaign, USA)
- Burr Settles (Carnegie Mellon University, USA)
- Kevin Small (Tufts University, USA)
- Katrin Tomanek (University of Jena, Germany)

Republish by : NORBERTUS CITRA IRAWAN,SP - www.competitions.co.nr

Related :

Copyright 2011 COMPETITION CONTEST AWARD FESTIVAL GAMES 2011 | Use For Forum Lowongan Kerja 2011 | Sponsored by INDOJOB.CO.BE
Enter Your Email To Recieve Update Contest in Your MailBox :