Seventeenth Conference on Computational Natural Language Learning
Sofia, Bulgaria

August 8-9, 2013


Final Call for Papers

CoNLL is the yearly conference organized by SIGNLL (the ACL Special
Interest Group on Natural Language Learning). This year, CoNLL will be
collocated with ACL 2013 in Sofia, Bulgaria. The shared task of CoNLL
will be Grammatical Error Correction, see details below.

Important Dates

* Paper submission deadline: April 17, 2013, 23:59 PST (GMT-8)

* Notification of acceptance: May 28, 2013

* Camera-ready copy deadline: June 10, 2013

* Conference: August 8-9, 2013 (straight after ACL 2013)


CoNLL is an international conference for research on natural language
learning. We invite the submission of papers on all aspects of
computational approaches to natural language learning, including, but
not limited to:

* Development and empirical evaluation of machine learning methods
  applied to any natural language or speech processing task in
  supervised, semi-supervised or unsupervised settings (e.g. structured
  prediction, graphical models, deep learning, relational learning,
  reinforcement learning, etc.).

* Theoretical analyses of learning-based approaches to natural
  language processing.

* Computational models of human language acquisition, language
  evolution and language change.

Invited Speakers

* Ben Taskar (University of Washington)

* Roger Levy (University of California, San Diego)

Special Topic of Interest: Compositional Semantics

For this edition of CoNLL, we particularly solicit papers that focus
on challenges and solutions within Compositional Semantics. 
Compositional approaches to semantics have their origin in formal
logic, but there is now a growing body of work that aims to integrate
such approaches into learning-based, statistical frameworks, often
building on recent advances in machine learning, such as structured
prediction, deep learning or distant supervision. This poses a number
of challenging questions, such as how to induce compositional meaning
representations from unlabelled, weakly labelled or fully labelled
natural language data, or how to reconcile inherently statistical
distributional approaches to lexical semantics with the principle of
compositionality. Advances in this area also hold substantial promise
for downstream applications such as sentiment analysis, question
answering or machine translation, making research in Compositional
Semantics appealing both from a pure and applied perspective.

Best Paper Award

As in recent CoNLL conferences, we are delighted to announce that
Google will sponsor a Best Paper Award for the authors of the highest
quality paper. The most important aspects in judging the quality of a
paper will be: originality, innovativeness, relevance, and impact of
the presented research.

Main Session Submission Details

A paper submitted to CoNLL-2013 must describe original, unpublished
work. Submit a full paper by April 17, 2013, 23:59 PST (GMT-8). Papers
may have up to eight (8) pages of content, with two (2) additional
pages of references, and will be presented orally or as a poster
presentation as determined by the program committee. The decisions as
to which papers will be presented orally and which as poster
presentations will be based on the nature rather than on the quality
of the work. There will be no distinction in the proceedings between
full papers presented orally and those presented as poster
presentations. Submission must be done electronically through the web
form at:


We require the use of the ACL 2013 LaTeX style files or Microsoft
Word Style files tailored for this year's conference.  Papers must
conform to the official ACL 2013 style guidelines.  Authors who are
unable to use these style files or submit a PDF file electronically
should contact the program co-chairs.Please refer to the

Format and ACL 2013 Style Files sections only at the following


Authors may also optionally submit a second document containing
supporting information such as proofs or algorithmic details.
Reviewers will have access to the supporting information and may refer
to it at their discretion. Any information that is critical to
understanding the paper should be included within the paper itself.

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 of no more than 300 words,
and information on whether the paper has been or will be
simultaneously submitted to other conferences (and if so which
conferences). The contact author of an accepted paper under multiple
submission will need to promptly inform the program co-chairs whether
he or she intends the accepted paper to appear in CoNLL-2013.  A paper
that is submitted to be included in CoNLL-2013 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 also follow the ACL 2013 style
and should have at most 8 pages of content plus at most 2 extra pages
for references only. At least one author must register for the
conference and present the paper. Please do not submit a paper if you
do not plan to attend the conference.

As in previous years, CoNLL-2013 will include a shared task which is
organized by a separate committee. The details of the shared task are
included in this CFP (see below). Please note the different submission
details and deadlines for the shared task.

Conference Chairs

Julia Hockenmaier
Department of Computer Science
University of Illinois at Urbana-Champaign

Sebastian Riedel
Department of Computer Science
University College London

Contact email: conll-2013 (at) cs.ucl.ac.uk

Shared Task: Grammatical Error Correction

CoNLL-2013 will continue the CoNLL tradition of having a high profile
shared task in natural language processing. This year's shared task
will be grammatical error correction. A participating system in this
shared task is given short English texts written by non-native
speakers of English. The system detects the grammatical errors present
in the input texts, and returns the corrected texts.

This task has gained popularity recently with the organization of the
HOO (Helping Our Own) shared tasks in 2011 and 2012. In the most
recent HOO shared task in 2012, on error detection and correction of
determiners and prepositions, 14 teams from around the world
participated and 85 systems were submitted to the shared task.

The grammatical error correction task is impactful since it is
estimated that hundreds of millions of people in the world are
learning English and they benefit directly from an automated grammar
checker. However, for many error types, current grammatical error
correction methods do not achieve a high performance and thus more
research is needed.

Instead of focusing on only determiner and preposition errors as in
HOO 2012, the CoNLL-2013 shared task will include a more comprehensive
list of error types, including determiner, preposition, noun number,
verb form, and subject-verb agreement errors. Extending into
more error types introduces the possibility of correcting multiple
interacting errors. Examples of such interacting errors include
determiner and noun number ('that cars' -> 'that car' or 'those cars')
and preposition and verb form ('an interest to study' > 'an interest
in studying').

Participating teams will be provided with common training data in
which grammatical errors have been annotated. Blind test data will be
used to evaluate the outputs of the participating teams using a common
scoring software and evaluation metric.

The shared task home page is accessible at:

Registration (NEW)

Registration for the shared task has begun. Please email the following
information to conll13st@gmail.com: name, email address, and
affiliation of the members of a participating team, with one team
member designated as the contact person. Upon registration, each
participating team will receive the training data and scorer and join
a discussion group for the shared task. A signed license agreement is
needed for receipt of the training data. A team can register at
anytime before the registration deadline, but early registration is
highly encouraged, since details of the shared task will be announced
on the discussion group. 54 teams have registered to participate in
the shared task this year.

Important Dates

December 17, 2012: announcement of shared task
January 17, 2013: set up of shared task website
February 5, 2013: registration begins and release of training set and scorer
March 5, 2013: registration deadline
April 28, 2013: test set available
May 1, 2013: systems' outputs collected
May 8, 2013: system results due to participants
May 15, 2013: shared task system papers due
May 24, 2013: reviews due
May 27, 2013: notification of acceptance
June 3, 2013: camera ready version of shared task system papers due
August 8-9, 2013: CoNLL-2013 conference

Shared Task Organizers

Hwee Tou Ng (Chair), National University of Singapore
Joel Tetreault, Nuance Communications
Siew Mei Wu, National University of Singapore
Yuanbin Wu, National University of Singapore
Christian Hadiwinoto, National University of Singapore


Questions about the CoNLL-2013 shared task can be sent to 


See http://ifarm.nl/signll/ and http://ifarm.nl/signll/conll/ for more
information about SIGNLL and CoNLL. Please direct questions about
SIGNLL and the CoNLL website to Erik, the SIGNLL Information Officer:

Erik Tjong Kim Sang
University of Groningen (The Netherlands)
erikt (at) xs4all.nl