Manchester, UK, August 16-17th 2008


The Twelfth Conference on Computational Natural Language Learning

Manchester, UK
August 16-17th 2008

Call for Papers

CoNLL is the yearly conference organized by SIGNLL (the ACL Special Interest Group on Natural Language Learning). Previous CoNLL meetings were held in Madrid (1997), Sydney (1998), Bergen (1999), Lisbon (2000), Toulouse (2001), Taipei (2002), Edmonton (2003), Boston (2004), Ann Arbor (2005), New York (2006) and Prague (2007). This year, 2008, CoNLL will be collocated with COLING in Manchester, UK.

See and for more information about SIGNLL and CoNLL. The official Web site of CoNLL-2008 can be found at

CoNLL is an international conference for research on natural language learning. We invite submission of papers about natural language learning topics, including, but not limited to:

  • Computational models of human language acquisition
  • Computational models of the evolution of language
  • Machine learning methods applied to natural language processing tasks (speech processing, phonology, morphology, syntax, semantics, discourse processing, language engineering applications)
  • Statistical methods (Bayesian learning, graphical models, kernel methods, statistical models for structured problems)
  • Symbolic learning methods (rule induction and decision tree learning, lazy learning, inductive logic programming, analytical learning, transformation-based error-driven learning)
  • Biologically-inspired methods (Neural Networks, Evolutionary Computing)
  • Reinforcement learning
  • Active learning, ensemble methods, meta-learning
  • Learning architectures for structural and relational NLP tasks
  • Computational learning theory analysis of language learning
  • Empirical and theoretical comparisons of language learning methods
  • Models of induction and analogy in linguistics

Special Topic of Interest

This year we wish to encourage the submission of papers on models that explain natural phenomena relating to human language. This has two strands.

The first concerns the central scientific problem addressed by CoNLL: the study of first language acquisition. The only systems that we know of that can process language accurately are humans; the acquisition of their first language by infant children is one of the central problems of cognitive science. We invite papers that address this problem using computational models; including papers that address purely linguistic aspects of the problem, papers that model psycholinguistic data, or papers that apply learning theoretic analysis to language acquisition.

The second theme is the central engineering problem: how to build systems that do something useful: we are interested in complete systems that solve real problems. Thus we particularly invite papers that are evaluated on naturally occurring annotations, such as machine translation, language modelling, or question answering. We are also interested in work that evaluates the contribution of components which predict linguist-defined intermediate structure such as part-of-speech tags, semantic roles, or syntactic analyses to the performance of real systems. Important issues such work might study are the correlation of the component's performance on the sub-task with its impact on the end system performance and alternative architectures for incorporating predictions from different components.

Shared Task

The shared task for this CoNLL is "Joint Parsing of Syntactic and Semantic Dependencies".

The task proposes the merging of both syntactic dependencies (extracted from the Penn Treebank ) and semantic dependencies (extracted both from PropBank and NomBank) under a unique unified representation. The task has several novel objectives:

  1. The first objective, performing Semantic Role Labeling (SRL) on a dependency-based representation, is to our knowledge novel. Furthermore, the SRL problem will address not only propositions centered around verbal predicates but also around nouns.
  2. The syntactic dependencies to be modeled will be more complex than the ones used in the previous CoNLL evaluations: Johansson and Nugues have shown that a richer set of syntactic dependencies improves semantic processing (Johansson & Nugues 2007).
  3. The proposed evaluation offers a practical framework to perform joint learning for the two problems.

Organised by

Mihai Surdeanu
Richard Johansson
Lluís Màrquez
Adam Meyers
Joakim Nivre

The organisers can be contacted at A detailed description is available at

Invited Speakers

Regina Barzilay (MIT)
Nick Chater (University College London)

Main Session Submissions

A paper submitted to CoNLL-2008 must describe original, unpublished work. Submit a full paper of no more than 8 pages in PDF format by April 29 2008, 11:59 GMT, electronically through the web form at

Only electronic submissions will be accepted. Submissions should follow the two-column format of ACL proceedings and should not exceed eight (8) pages, including references. We strongly recommend the use of the Coling 2008 LaTeX style files or Microsoft Word Style files tailored for this year's conference. Papers must conform to the official Coling 2008 style guidelines. Authors who cannot submit a PDF file electronically should contact the program co-chairs.

Since reviewing will be blind, the paper should not include the authors' names and affiliations, and there should be no self-references that reveal the authors' identity. In the submission form, you will be asked for the following information: paper title, authors' names, affiliations, and email addresses, contact author's email address, a list of keywords, abstract, and an indication of whether the paper has been simultaneously submitted to other conferences (and if so which conferences). The contact author of an accepted paper under multiple submissions should inform the program co-chairs immediately whether he or she intends the accepted paper to appear in CoNLL-2008. A paper that appears in CoNLL-2008 must be withdrawn from other conferences.

Authors of accepted submissions are to produce a final paper to be published in the proceedings of the conference, which will be available at the conference for participants, and distributed afterwards by ACL. Final papers must follow the Coling 2008 style and are due 1 July, 2008.

Shared Task Submissions

See the shared task web page ( for updated information.

Important Dates

Paper submission deadline: 29 April 2008, 11:59 GMT
Notification of acceptance of papers: 6 June 2008
Deadline for camera-ready papers: 1 July 2008
Conference: August 16-17, 2008

Conference Organizers

Alex Clark
Department of Computer Science
Royal Holloway, University of London
alexc (at)

Kristina Toutanova
Microsoft Research
kristout (at)

Shared Task Organizers

Mihai Surdeanu
Richard Johansson
Lluís Màrquez
Adam Meyers
Joakim Nivre

Information Officer

Erik Tjong Kim Sang
University of Amsterdam (The Netherlands)
erikt (at)

Program Committee

  • Steve Abney, University of Michigan, USA
  • Eneko Agirre, University of the Basque Country, Spain
  • Galen Andrew, Microsoft Research, USA
  • Tim Baldwin, University of Melbourne, Australia
  • Regina Barzilay, Massachusetts Institute of Technology, USA
  • Roberto Basili, University of Roma, Tor Vergata, Italy
  • Phil Blunsom, University of Edinburgh, UK
  • Thorsten Brants, Google Inc, USA
  • Paula Buttery, Cambridge University, UK
  • Xavier Carreras, Polytechnical University of Catalunya, Spain
  • Eugene Charniak, Brown University, USA
  • Nick Chater, University College London, UK
  • Ciprian Chelba, Google Inc, USA
  • Colin Cherry, Microsoft Research, USA
  • Stephen Clark, Oxford University, UK
  • James Cussens, University of York, UK
  • Walter Daelemans, University of Antwerp, Belgium
  • Hal Daumé III, University of Utah, USA
  • Jenny Finkel, Stanford University, USA
  • Radu Florian, IBM, USA
  • Dayne Freitag, Fair Isaac Corporation, USA
  • Michel Galley, Stanford University, USA
  • Jianfeng Gao, Microsoft Research, USA
  • Daniel Gildea, University of Rochester, USA
  • Sharon Goldwater, University of Edinburgh, UK
  • Jan Hajic, Charles University, Czech Republic
  • James Henderson, University of Edinburgh, UK
  • Andrew Hickl, Language Computer Corporation, USA
  • Liang Huang, University of Pennsylvania, USA
  • Rie Johnson (formerly, Ando), RJ Research Consulting, USA
  • Rohit Kate, UT Austin, USA
  • Philipp Koehn, University of Edinburgh, UK
  • Rob Koeling, University of Sussex, UK
  • Anna Korhonen, Cambridge University, UK
  • Shalom Lappin, King's College, London, UK
  • Roger Levy, UC San Diego, USA
  • Percy Liang, UC Berkeley, USA
  • Rob Malouf, San Diego State University, USA
  • Yuji Matsumoto, Nara Institute of Science and Technology, Japan
  • Diana McCarthy, University of Sussex, UK
  • Rada Mihalcea, University of North Texas, USA
  • Alessandro Moschitti, University of Rome Tor Vergata, Italy
  • Lluís Màrquez, Technical University of Catalonia, Spain
  • John Nerbonne, University of Groningen, The Netherlands
  • Vincent Ng, University of Texas Dallas, USA
  • Hwee-Tou Ng, National University of Singapore, Singapore
  • Joakim Nivre, Växjö University and Uppsala University, Sweden
  • Franz Josef Och, Google, Inc., USA
  • Miles Osborne, University of Edinburgh, UK
  • Slav Petrov, UC Berkeley, USA
  • David Powers, Flinders University, Australia
  • Chris Quirk, Microsoft Research, USA
  • Ari Rappoport, The Hebrew University of Jerusalem, Israel
  • Ellen Riloff, University of Utah, USA
  • Dan Roth, University of Illinois at Urbana-Champaign, USA
  • William Sakas, Hunter College, CUNY, USA
  • Anoop Sarkar, Simon Fraser University, Canada
  • Richard Sproat, University of Illinois at Urbana-Champaign, USA
  • Suzanne Stevenson, University of Toronto, Canada
  • Mihai Surdeanu, Polytechnical University of Catalunya, Spain
  • Charles Sutton, UC Berkeley, USA
  • Antal van den Bosch, Tilburg University, The Netherlands
  • Dekai Wu, The Hong Kong University of Science & Technology, Hong Kong
  • Charles Yang, University of Pennsylvania, USA   Last update: June 18, 2008