2011Q3 Reports: SIGNLL

From Admin Wiki
Revision as of 10:24, 4 June 2011 by JoakimNivre (talk | contribs)
Jump to navigation Jump to search

ACL SIGNLL Annual Report (2010-2011)

by Joakim Nivre and Lluís Màrquez

The goals of SIGNLL, ACL's special interest group on natural language learning, are to promote and inform about research on computational modeling of learning in natural language. These are served by (i) the maintenance of an informative and up-to-date website and associated mailing list, and (ii) the organization of annual events (the CoNLL conference and the CoNLL shared task), and support of other related activities.

The web-pages, located at URL http://www.aclweb.org/signll/ and maintained by Erik Tjong Kim Sang, remain an important source of information, complemented by an email list for announcements for SIGNLL-related events. On the web-site, links can be found to relevant associations, networks, research cooperations, research departments, groups, institutes, mailing lists, archives, journals, bulletins, conference reports, online papers (including all papers of all CoNLL proceedings), online courses and slides, bibliographies, software, corpora, companies, meta-information sources, etc.

Currently, SIGNLL has 339 members. The SIGNLL officers are president Joakim Nivre (Uppsala University, Sweden), secretary Lluís Màrquez (Technical University of Catalonia, Spain), and information officer Erik Tjong Kim Sang. The current office period for president and secretary runs from November 1, 2009 to October 31, 2011, so new elections will be held after the summer of 2011.

Apart from the officers, SIGNLL also has two consultative committees. The SIGNLL Steering Committee, composed by all past SIGNLL officers: Antal van den Bosch, Claire Cardie, Walter Daelemans, Hwee Tou Ng, David Powers, and Dan Roth; and the larger SIGNLL International Advisory Board (see http://ifarm.nl/signll/about/#officers, for a complete description of SIGNLL officers and boards). David Yarowsky acts as the SIGDAT Liaison Representative.

CoNLL-2011

The Fifteenth SIGNLL Conference on Computational Natural Language Learning, CoNLL-2011, will be held in Portland, Oregon, 23-124 June 2011, in conjunction with ACL 2011. Program co-chairs are Sharon Goldwater and Chris Manning. The special topic of interest of the 2011 edition is Massive, Linked Text Data.

CoNLL 2011 received 82 submissions, of which 4 were eventually withdrawn. Of the remaining 78 papers, 27 were selected to appear in the conference program for an acceptance rate of 35%. The invited speakers are Bruce Hayes (UCLA) and Yee Whye Teh (Gatsby Unit, UCL) and their talks will cover computational linguistics for studying language in people and bayesian tools for natural language learning, respectively.

As in previous years, the CoNLL-2011 best paper award is sponsored by Google. A novelty this year is that there will also be an award for best student paper. More information can be found at the conference website: http://www.cnts.ua.ac.be/conll2011/.

CoNLL-2011 Shared Task

As in previous years, CoNLL-2011 has a shared task, "Modeling Unrestricted Coreference in OntoNotes". The shared task is completely new and was selected from a set of 5 proposals submitted to the SIGNLL call for shared tasks in September 2010. A total of 22 teams have participated in the shared task, which demonstrates its high interest in the community. As usual, the shared task papers will be collected into an accompanying volume of the CoNLL-2011 proceedings.

The task maintains its own website where all the details (including datasets and results) can be found at: http://conll.bbn.com/.

Other Activities

  • SIGNLL is also endorsing the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis, to be held in conjunction with ACL 2011 in Portland, Oregon. Workshop website: http://gplsi.dlsi.ua.es/congresos/wassa2011/.
  • In July-August 2011, SIGNLL will launch a call for shared task proposals to select the task to be run in CoNLL-2012. A designated committee will judge the submitted proposals and declare the selected task no later than October 2011.