<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">FYI<br><br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<br>
*******************************************************************************<br>
SANCL 2012 - NAACL-HLT Workshop on Syntactic Analysis of Non-Canonical<br>
Language<br>
*******************************************************************************<br>
<br>
The first Workshop on Syntactic Analysis of Non-Canonical Language will be<br>
held in conjunction with the 2012 Conference of the North American Chapter<br>
of the Association for Computational Linguistics: Human Language<br>
Technologies (NAACL-HLT 2012) which will take place in June, 3-8, 2012 in<br>
Montreal, Canada.<br>
<br>
<br>
Important Dates<br>
---------------<br>
Apr 04, 2012 Paper submission deadline<br>
Apr 27, 2012 Notification of acceptance<br>
May 07, 2012 Camera-ready deadline<br>
Jun 08, 2012 SANCL workshop at NAACL-HLT 2012<br>
<br>
<br>
Workshop Description<br>
--------------------<br>
The SANCL workshop aims to provide a forum for all researchers interested<br>
in syntactic analysis and parsing of language that is “non-canonical”. By<br>
that term we mean structures with characteristics deviating from the<br>
standard written form of the language. A case in point is spoken language,<br>
but also the language of social media, computer-mediated communication in<br>
general, the interlanguage produced by language learners, or historical<br>
data. All of these pose challenges for parsing models trained on edited<br>
newspaper text as well as for the theoretical analysis of these<br>
structures.<br>
<br>
<br>
Scope and Topics<br>
----------------<br>
We aim to encourage a cross-fertilisation of ideas amongst researchers<br>
working on different but related problems, such as<br>
- What is the best strategy for parsing non-canonical language?<br>
- Should we treat parsing of non-canonical language as a problem of<br>
robustness or domain adaptation?<br>
- Or would it be better to develop new training data sets addressing<br>
the particular properties of the data?<br>
- What are the pros and cons of a one-size-fits-all annotation approach<br>
and of applying annotation schemes developed for standard written text<br>
to non-canonical data?<br>
- Can insights gained from parsing one type of non-canonical text help<br>
in parsing another?<br>
- What are the challenges of handling the often heterogeneous nature of<br>
the data (e.g. code-switching)?<br>
- What role does pre-processing play in the parsing of non-canonical data?<br>
- To what extent is it necessary or desirable to perform full parsing<br>
for some kinds of non-canonical text?<br>
- From a theoretical perspective, what are the appropriate analyses for<br>
non-canonical structures?<br>
- How should new linguistic forms emerging from social media be<br>
analysed, e.g. the use of hashtags in Twitter?<br>
- What is the optimal unit of analysis?<br>
- For non-sentential units (frequent in spoken language) and especially<br>
for elliptical utterances: what kind of information is necessary for a<br>
meaningful analysis? Depending on the application, categories like "NP"<br>
or "PP" might not sufficient.<br>
<br>
Contributions to the workshop should address the adequate syntactic<br>
representation as well as the unit of analysis for the task at hand. We<br>
welcome both theoretical and practical contributions for any grammatical<br>
framework, any parsing approach and any language.<br>
<br>
<br>
Submission Details<br>
------------------<br>
Authors are invited to submit long or short papers on original,<br>
unpublished work addressing these (or related) topics. Long papers may<br>
consist of up to 8 pages of content plus two extra pages for references;<br>
short papers may consist of 4 pages of content including references.<br>
Papers should be formatted according to the NAACL 2012 guidelines (for<br>
more information please visit<br>
<a href="http://www.naaclhlt2012.org/conference/conference.php" target="_blank">http://www.naaclhlt2012.org/conference/conference.php</a>).<br>
<br>
As the reviewing will be blind, the paper must not include the authors'<br>
names and affiliations. Furthermore, self-references that reveal the<br>
author's identity, e.g., "We previously showed (Smith, 1991) ..." must be<br>
avoided. Instead, use citations such as "Smith previously showed (Smith,<br>
1991) ..." Papers that do not conform to these requirements will be<br>
rejected without review. In addition, please do not post your submissions<br>
on the web until after the review process is complete.<br>
<br>
Papers that have been or will be submitted to other meetings or<br>
publications must indicate this at submission time. Please visit the<br>
workshop web page (<a href="https://sites.google.com/site/sancl2012" target="_blank">https://sites.google.com/site/sancl2012</a>) for more<br>
details.<br>
<br>
Papers will be accepted until Apr 04, 2012, 11:59pm (PDT, GMT-8) in PDF<br>
format via the START system<br>
(<a href="https://www.softconf.com/naaclhlt2012/SANCL2012" target="_blank">https://www.softconf.com/naaclhlt2012/SANCL2012</a>).<br>
<br>
<br>
Shared Task<br>
-----------<br>
The SANCL 2012 workshop will host the *first shared task on parsing<br>
English web text* organised by Google. A session in the workshop will be<br>
devoted to presenting and discussing the results of this shared task. For<br>
more details, please visit<br>
<a href="https://sites.google.com/site/sancl2012/home/shared-task" target="_blank">https://sites.google.com/site/sancl2012/home/shared-task</a><br>
<br>
<br>
Workshop Organizers<br>
-------------------<br>
Ozlem Cetinoglu (IMS Stuttgart, Germany)<br>
Jennifer Foster (NCLT, DCU, Ireland)<br>
Ines Rehbein (Potsdam University, Germany)<br>
<br>
<br>
Shared Task Organizers<br>
----------------------<br>
Slav Petrov (Google Research, USA)<br>
Ryan McDonald (Google Research, USA)<br>
<br>
<br>
Program Committee<br>
-----------------<br>
Bernd Bohnet (IMS Stuttgart, Germany)<br>
Aoife Cahill (Educational Testing Service, USA)<br>
Marie Candito (University of Paris 7, France)<br>
John Carroll (University of Sussex, UK)<br>
Jinho Choi (University of Colorado at Boulder, USA)<br>
Eric de la Clergerie (INRIA, France)<br>
Markus Dickinson (Indiana University, USA)<br>
Steffi Dipper (University of Bochum, Germany)<br>
Gulsen Eryigit (Istanbul Technical University, Turkey)<br>
Stefan Evert (University of Darmstadt, Germany)<br>
Kim Gerdes (University of Paris 3, France)<br>
Masato Hagiwara (Rakuten Institute of Technology, USA)<br>
Ron Kaplan (Microsoft, USA)<br>
Jonas Kuhn (IMS Stuttgart, Germany)<br>
Sandra Kübler (Indiana University, USA)<br>
Joseph Le Roux (Université Paris-Nord, France)<br>
Anke Lüdeling (Humboldt-University of Berlin, Germany)<br>
David McClosky (Stanford University, USA)<br>
Detmar Meurers (University of Tübingen, Germany)<br>
Joakim Nivre (Uppsala University, Sweden)<br>
Lilja Øvrelid (University of Oslo, Norway)<br>
Brian Roark (Oregon Health & Science University, USA)<br>
Kenji Sagae (University of Southern California, USA)<br>
Djamé Seddah (University of Paris 4, France)<br>
Reut Tsarfaty (Uppsala University, Sweden)<br>
Josef van Genabith (Dublin City University, Ireland)<br>
Heike Zinsmeister (University of Konstanz, Germany)<br>
<br>
<br>
Contact Information<br>
-------------------<br>
For general questions about the workshop, please email<br>
<a href="mailto:sancl2012contact@gmail.com" target="_blank">sancl2012contact@gmail.com</a>. For specific questions about the shared task,<br>
please email the shared task organizers (<a href="mailto:parsingtheweb@gmail.com" target="_blank">parsingtheweb@gmail.com</a>).<br>
Additional information about SANCL 2012 can be found at<br>
<a href="https://sites.google.com/site/sancl2012" target="_blank">https://sites.google.com/site/sancl2012</a>.<br>
<br>
</blockquote></div><br>
</blockquote></div><br>