[Elsnet-list] EACL 2009: Second Call for Papers
joakim.nivre at lingfil.uu.se
Tue Jun 24 17:41:19 CEST 2008
-------------- next part --------------
EACL 2009: Second Call for Papers
March 30 - April 3, 2009
Submission deadline: October 10, 2008
EACL 2009 is the 12th Conference of the European Chapter of the Association
for Computational Linguistics. The conference invites the submission of
papers on substantial, original, and unpublished research on all aspects of
computational linguistics, including, but not limited to:
- phonetics, phonology, and morphology;
- spoken language processing and language modeling;
- word segmentation, tagging, and chunking;
- syntax, parsing, and grammar formalisms;
- lexical semantics and word sense disambiguation;
- compositional semantics and textual entailment;
- pragmatics, discourse, and dialogue;
- lexicon, lexical databases, and ontologies;
- generation and summarization;
- information retrieval, question answering, and information extraction;
- machine translation and multilingual systems;
- dialogue systems and multimodal systems;
- language resources and tools, and resources for lesser studied languages;
- linguistic, psychological, and mathematical models of language;
- machine learning and algorithms for natural language;
- evaluation methodology.
Papers should describe original work; they should emphasize completed work
rather than intended work, and should indicate clearly the state of
completion of the reported results. A paper accepted for presentation at
EACL 2009 cannot be presented or have been presented at any other meeting
with publicly available published proceedings. Papers that are being
submitted to other conferences or workshops must indicate this on the
Review and Selection
Reviewing of papers will be double-blind, and all submissions will receive
three independent reviews. Final decisions on the program will be made by
the Program Committee, consisting of the Program Co-Chairs and Area Chairs.
Submissions will be assessed with respect to appropriateness, clarity,
soundness/correctness, meaningful comparison, originality/innovativeness,
and impact of ideas or results. For more information about the review
criteria, see the review form appended below.
Publication and Presentation
All papers that are accepted will be published in the proceedings of the
conference, and will be presented as a poster or an oral presentation.
Authors will be asked on submission to state their preferred mode of
presentation, and the program committee will attempt to fulfill as many
of these preferences as possible, organizational factors permitting.
EACL 2009 will additionally aim to give poster presentations higher
status than usual (by scheduling, physical arrangement, combination with
refreshments). The proceedings will not distinguish long papers by
All submissions must be electronic in PDF and must follow the two-column
format of EACL proceedings. Authors are strongly recommended to use the
style files available on the conference web site. The maximum length of
a manuscript is eight (8) pages of content and one (1) additional page
of references. The page limits have to be strictly observed.
As reviewing will be double-blind, the paper should not include the
authors' names and affiliations. Furthermore, self-references that reveal
the author's identity, e.g., "We previously showed (Smith, 1991) ...",
should be avoided. Instead, use citations such as "Smith previously
showed (Smith, 1991) ...". (Do not use anonymous citations.) Do not
include acknowledgments. Papers that do not conform to these requirements
will be rejected without review.
The deadline for submission is 23:59 CET on October 10, 2008. Additional
instructions for electronic submission will be posted on the conference
website at http://www.eacl2009.gr.
Paper submission deadline: October 10, 2008
Notification of acceptance: December 19, 2008
Camera-ready papers due: February 13, 2008
EACL 2009 Conference: March 30 - April 3, 2009
Ann Copestake, University of Cambridge, UK
Franciska de Jong, University of Twente, the Netherlands
General Chair: Alex Lascarides (University of Edinburgh, UK)
Program Co-Chairs: Claire Gardent (CNRS/LORIA, Nancy, France)
Joakim Nivre (Vaxjoniversity and Uppsala
Area Chairs: Anja Belz (University of Brighton, UK)
Sabine Buchholz (Toshiba Research Europe, UK)
Chris Callison-Burch (Johns Hopkins University, USA)
Philipp Cimiano (University of Karlsruhe, Germany)
Anna Korhonen (University of Cambridge, UK)
Kimmo Koskenniemi (University of Helsinki, Finland)
Bernardo Magnini (FBK-irst, Italy)
Stephan Oepen (University of Oslo, Norway)
Richard Power (The Open University, UK)
Giuseppe Riccardi (University of Trento, Italy)
Maarten de Rijke (University of Amsterdam, the
Local Chair: Vangelis Karkaletsis (NCSR Demokritos, Greece)
Local Co-Chairs: Ion Androutsopoulos (Athens University of
Economics and Business, Greece)
Stelios Piperidis (Institute for Language and
Speech Processing, Greece)
Appendix: Review Form
EACL 2009: 12th Conference of the European Chapter of the
Association for Computational Linguistics
Please evaluate the submission according to the criteria below.
Does the paper fit in EACL 2009?
(EACL 2009 invites papers on all aspects of computational
linguistics, theoretical and empirical, linguistic and
computational, fundamental and applied; see the
Call for Papers.)
5 = Appropriate for EACL 2009. (<i>most submissions</i>)
4 = Linguistics or computer science but not typical EACL material.
3 = Possibly relevant to the audience but not really EACL material.
2 = Only marginally relevant.
1 = Inappropriate.
For the reasonably well-prepared reader, is it clear what was
done and why? Is the paper well-written and well-structured?
Does the English or the mathematics need cleaning up? Would
the explanation benefit from more examples or pictures?
Is there sufficient detail for an expert to validate the work,
e.g., by replicating experiments or filling in theoretical steps?
(Take into account whether any obscurity or minor English errors
could be fixed with relatively little effort, or whether the
paper requires more work than is likely to be carried out in the
few weeks available.)
5 = Admirably clear.
4 = Understandable by most readers.
3 = Mostly understandable to me with some effort.
2 = Important questions were hard to resolve even with effort.
1 = Much of the paper is confusing.
First, is the general approach sound and well-chosen given the
purpose of the paper? Secondly, can one trust the claims of the
paper -- are they supported by proper linguistic analysis,
experiments, (other) empirical results, proofs, or other
(Note that the kind of support required will be different for
different types of papers, theoretical or empirical, linguistic
or computational, fundamental or applied. Please try to assess
whether the justification offered is adequate given the goals
of the paper.)
5 = The approach is very apt, and the claims are convincingly
4 = Generally solid work, though I have a few suggestions about
how to strengthen the approach or its justification.
3 = Fairly reasonable work. The approach is not bad, and at
least the main claims are probably correct, but I am not
entirely ready to accept them (based on the material in
2 = Troublesome. There are some ideas worth salvaging here,
but the work should really have been done or evaluated
differently, or justified better.
1 = Fatally flawed.
Does the author make clear where the problems and methods sit
with respect to existing literature? Are the references
adequate? Are the new contributions meaningfully compared to
the state of the art in the area, e.g., in terms of
experimental results, linguistic coverage, or theoretical
5 = Precise and complete comparison with related work. Good
job given the space constraints.
4 = Mostly solid bibliography and comparison, but I have some
3 = Bibliography and comparison are somewhat helpful, but it
could be hard for a reader to determine exactly how this
work relates to previous work.
2 = Only partial awareness and understanding of related work,
or a flawed comparison to the state of the art.
1 = Little awareness of related work, or lacks necessary
How original is the approach? Does the paper break new ground in
topic, methodology, or content? How exciting and innovative is
the research it describes?
(Note that a paper can score high for originality even if the
benefit of the approach is not yet fully justified.)
5 = Surprising: Noteworthy new problem, theory, methodology, or
4 = Creative: Relatively few people in our community would have
put these ideas together.
3 = Somewhat conventional: A number of people could have come up
with this if they thought about it for a while.
2 = Rather boring: Obvious, or a minor modification on a familiar
1 = Significant portions have actually been done before or done
Impact of Ideas or Results
How significant is the work described? If the ideas are novel,
will they also be useful or inspirational? If the claims and
results are sound, are they also important?
5 = Will affect the field by altering other people's choice of
research topics or basic approach.
4 = Some of the ideas or results will substantially help other
people's ongoing research.
3 = Interesting but not too influential. The work will be cited,
but mainly for comparison or as a source of minor
2 = Marginally interesting. May or may not be cited.
1 = Will have no impact on the field.
There are many good submissions competing for a place at EACL
2009. How important is it to feature this one? Will people
learn a lot by reading this paper or seeing it presented at
In deciding your ultimate recommendation, please think over
all your scores above. But remember that no paper is perfect,
and remember that we want a conference full of interesting,
diverse and timely work. If a paper has some weaknesses, but
you really got a lot out of it, feel free to fight for it. If
a paper is solid but you could live without it, let us know
that you're ambivalent. Remember also that the author has a
few weeks to address reviewer comments before the
Should the paper be accepted or rejected?
5 = Exciting: I'd fight to get it accepted.
4 = Worthy: I would like to see it accepted.
3 = Borderline: I'm ambivalent about this one.
2 = Mediocre: I'd rather not see it in the conference.
1 = Poor: I'd fight to have it rejected.
5 = Positive that my evaluation is correct. I read the paper
very carefully and am very familiar with related work.
4 = Quite sure. I tried to check the important points
carefully, and checked for uncited prior work. It's
unlikely, though conceivable, that I missed something
that should affect my ratings.
3 = Pretty sure, but there's a chance I missed something.
Although I have a good feel for this area in general, I
did not carefully check the paper's details, e.g., math,
linguistic data, experimental design, novelty.
2 = Willing to defend evaluation, but it is fairly likely
that I missed some details, didn't understand some
central points, or can't be sure about the novelty of
1 = Not my area, or paper is very hard to understand. My
evaluation is just an educated guess.
Mode of Presentation
We would like your opinion as to whether the paper is best
presented as a talk or as a poster. Your decision should
be based on whether you believe the best way to present
the work is via a conversation in a small group, or via a
monologue. For example, if a paper argues in favor of a
general research agenda, and this agenda can be understood
without understanding every single detail, then one could
argue that the paper is best presented as a talk/monologue.
By contrast, if to appreciate the main point of the paper
one must understand fully all its technical details, which
in turn you view as hard to get across in a 20 minute talk,
then the paper may be construed to be more suitably
presented as a poster/via conversation in small groups.
Please give us your opinion about what the mode of
presentation should be for this paper:
(Note that this is not a question about the quality of the
work, so a low score here does not imply a low overall
3 = This work would be best presented as a poster.
2 = This work could be presented equally well as a talk or
as a poster.
1 = This work would be best presented as a talk.
Impact on Related Fields
Would this paper be of interest to communities from related
fields, and if so, which one?
(Note that this is not a question about the quality of the
work, so a low score here does not imply a low overall
3 = This paper is equally relevant to a related field as it
is to CL
2 = This paper is somewhat relevant to a related field
1 = This paper is only relevant to CL.
If your answer is "2" or "3" then please indicate the
field(s) you think this paper is relevant to:
_ Linguistics (including phonetics)
_ Computer Science
_ Cognitive science (including psychology)
_ Statistics (including machine learning)
_ Other. Please specify: ................
Please supply detailed comments to back up your rankings.
These comments will be forwarded to the authors of the
paper. The comments will help the committee decide the
outcome of the paper, and will help justify this decision
for the authors. Moreover, if the paper is accepted, the
comments should guide the authors in making revisions for
a final manuscript. Hence, the more detailed you make your
comments, the more useful your review will be -- both for
the committee and for the authors.
Enter comments here:
Confidential Comments for Committee
You may wish to withhold some comments from the authors,
and include them solely for the committee's internal use.
For example, you may want to express a very strong
(negative) opinion on the paper, which might offend the
authors in some way. Or, perhaps, you wish to write
something which would expose your identity to the authors.
If you wish to share comments of this nature with the
committee, this is the place to put them.
More information about the Elsnet-list