[Elsnet-list] First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Language (SPMRL-SANCL 2014) - 1st CFP

Joel Tetreault tetreaul at gmail.com
Wed Mar 12 17:59:34 CET 2014


(apologies for cross-posting)




  *First Joint Workshop on Statistical Parsing of Morphologically Rich
Languages and Syntactic Analysis of Non-Canonical Language *

*SPMRL-SANCL 2014*

ENDORSED BY SIGPARSE <http://www.cs.cmu.edu/~sigparse/>

Co-located with COLING 2014 <http://www.coling-2014.org/>, August 23-24 in
Dublin, Ireland

http://www.spmrl.org/spmrl-sancl2014.html

Submission Deadline:  May 02, 2014


 The CFP below is for the SPMRL-SANCL *Main*
Workshop<http://www.spmrl.org/spmrl-sancl2014.html>.
 The workshop also features:

·         Second Shared Task on Semi-Supervised Parsing of Morphologically
Rich Languages <http://www.spmrl.org/spmrl2014-sharedtask.html>

·         Special Track on the Syntactic Analysis of Non-Canonical
Language<http://www.spmrl.org/sancl-posters2014.html>

Follow the links for more details on the Shared Task and Special Track.

*Motivation*

Statistical parsing of morphologically-rich languages (MRLs) and syntactic
analysis of non-canonical languages (NCL) have shown several similar
properties and challenges in recent research. Therefore, this year we
organize a joint workshop of these two research communities, to foster
cross-pollination
of ideas and technology for both.

Statistical parsing of morphologically-rich languages has repeatedly been
shown to exhibit non-trivial challenges including, among others, sparse
lexica in the face of rich inflectional systems, parsing deficiency in the
face of free word order and treebank annotation idiosyncrasies in the face
of morphosyntactic interactions.

Similar problems arise for parsing of non-canonical languages. Besides
technical issues such as lexical sparseness and ad-hoc structures, we also
face theoretical problems including constructions that do not occur, or
very seldom occur, in standard language, such as verbless sentences or
complex hashtags.

The first joint SPMRL-SANCL workshop addresses both the challenge of
parsing MRLs and NCL. It provides a forum for researchers addressing the
often overlapping issues of both fields with the goal of identifying
cross-cutting issues in the annotation and parsing methodology for such
languages.

*Areas of Interest*

The areas of interest of the SPMRL-SANCL workshop include, but are not
limited to, the following list of topics:

·            applying cutting-edge parsing techniques to new languages and
domains

·            identifying the strengths and weaknesses of current parsing
techniques when applied to morphologically-rich and/or non-canonical
language

·            developing techniques that are targeted at improving parsing
quality of morphologically-rich and/or non-canonical language

·            developing models and architectures that explicitly integrate
morphological analysis and parsing

·            addressing data sparseness due to lexical variants,
out-of-vocabulary
(OOV) words and noise, ad-hoc syntactic rules, non-canonical word order,
ungrammatical structures, or disfluencies

·            using insights from parsing and associated processing problems
to motivate decisions in the creation of new syntactically annotated
corpora ("treebanks"), especially in domains, genres, and languages that
are not yet, or hardly covered; tag set design

·            discussing the role of parsing in higher-level NLP
applications involving MRLs and NCLs, e.g. syntax-enhanced MT and semantic
analysis.



*Second Shared Task on Semi-Supervised Parsing of Morphologically Rich
Languages*


 The workshop will also host the second shared task on parsing
morphologically rich language (see
http://spmrl.org/spmrl2014-sharedtask.html).  The first shared task was
held in conjunction with SPMRL 2013.  It helped show that carefully
engineered approaches can help to push the envelope on languages such as
Hungarian, Basque, Hebrew and Polish, where the shared task results
for constituency
parsing are the best current known for those languages. The task embodied a
focus on realistic scenarios (no gold tokenization, no gold part-of-speech
or morphology), as well as meaningful evaluation measures, including a
cross-framework evaluation that permits comparisons between constituent and
dependency parsing models.

The second installment of the Shared Task will feature a similar range of
languages. Moreover, it will also consider a semi-supervised scenario where
larger quantities of in-domain text are available. These unlabeled data are
aimed to be used for self-training, co-training, lexical acquisition,
generating word clusters, word embeddings and so on. A separate call for
the Shared Task is forthcoming.

*Special Track on Syntactic Analysis of Non-Canonical Language*

In addition to regular paper submissions, we solicit poster submissions
addressing the syntactic analysis of frequent phenomena of non-canonical
language, which are difficult to annotate and parse using conventional
annotation schemes. Cases in point are the representation of verbless
utterances in a dependency scheme, the pros and cons of different
representations of disfluencies for statistical parsing, or the analysis of
complex hashtags which incorporate and merge different syntactic arguments
into one token. The posters should focus, in more detail, on one more of
these issues.  More details on the submission categories for the poster
session can be found below and at: http://spmrl.org/sancl-posters2014.html

*Important Dates*

·         Submission Date: May 02, 2014 (23:59 UTC - 12)

·         Author Notification: June 06, 2014

·         Camera-ready papers due: June 27, 2014

·         Workshop: August 23 or 24, 2014



*How to Submit*



We solicit the following submission categories:



·         Long papers (up to 11 pages with unlimited references)

·         Short papers (up to 6 pages with unlimited references)

·         Abstracts (500 words excluding examples/references, for SANCL
poster topics only)

·         Shared task paper submissions (format will be disclosed later)



Long papers are most appropriate for presenting substantial and completed
research addressing a topic relevant to either SANCL or SPMRL.

Short papers are suited for presenting work in progress, position papers or
short, focused contributions, relevant to either SANCL or SPMRL (including
the poster session topics described above and, in more detail,
here<http://www.spmrl.org/sancl-posters2014.html>
).

Both long and short papers should present original, unpublished research.
They will be peer reviewed and will be presented as either an oral talk or
as a poster at the workshop. Long/short papers will be included in the
proceedings. Abstract submissions are most appropriate for presenting an
idea for an analysis for one or more of the poster topics. In contrast to
long/short paper submissions, abstract submissions do not need to back up
their ideas with experimental results. Abstract submission will receive a
yes/no review and will not be included in the proceedings.

Submissions will be accepted in PDF format via the START system and must
conform to the COLING 2014 formatting instructions:
http://www.coling-2014.org/call-for-papers.php



*Organizers*

*Workshop*

·            Yoav Goldberg (Bar Ilan University, Israel)

·            Yuval Marton (Microsoft Corp., US)

·            Ines Rehbein (Potsdam University, Germany)

·            Yannick Versley (Heidelberg University, Germany)

·            Özlem Çetinoğlu (University of Stuttgart, Germany)

·            Joel Tetreault (Yahoo! Labs, US)


*SANCL Special Session*

·            Ines Rehbein (Potsdam University, Germany)

·            Özlem Çetinoğlu (University of Stuttgart, Germany)

·            Djamé Seddah (Université Paris Sorbonne & INRIA's Alpage
Project, France)

·            Joel Tetreault (Yahoo! Labs, US)



*Shared task*

·            Sandra Kübler (Indiana University, US)

·            Djamé Seddah (Université Paris Sorbonne & INRIA's Alpage
Project, France)

·            Reut Tsarfaty (Uppsala University, Sweden)



*Program committee*

·            Bernd Bohnet (University of Birmingham, UK)

·            Marie Candito (University of Paris 7, France)

·            Aoife Cahill (Educational Testing Service Inc., US)

·            Jinho D. Choi (University of Massachusetts Amherst, US)

·            Grzegorz Chrupala (Tilburg University, Netherlands)

·            Gülşen Cebiroğlu Eryiğit (Istanbul Technical University,
Turkey)

·            Markus Dickinson (Indiana University, US)

·            Stefanie Dipper (Ruhr-Universität Bochum, Germany)

·            Jacob Eisenstein (Georgia Institute of Technology, US)

·            Richard Farkas (University of Szeged, Hungary)

·            Jennifer Foster (Dublin City University, Ireland)

·            Josef van Genabith (DFKI, Germany)

·            Koldo Gojenola (University of the Basque Country, Spain)

·            Spence Green (Stanford University, US)

·            Samar Husain (Potsdam University, Germany)

·            Sandra Kübler (Indiana University, US)

·            Joseph Le Roux (Université Paris-Nord, France)

·            John Lee (City University of Hong Kong, China)

·            Wolfgang Maier (University of Düsseldorf, Germany)

·            Takuya Matsuzaki (University of Tokyo, Japan)

·            David McClosky (IBM Research, US)

·            Detmar Meurers (University of Tübingen, Germany)

·            Joakim Nivre (Uppsala University, Sweden)

·            Kemal Oflazer (Carnegie Mellon University, Qatar)

·            Adam Przepiorkowski (ICS PAS, Poland)

·            Owen Rambow (Columbia University, US)

·            Kenji Sagae (University of Southern California, US)

·            Benoit Sagot (Inria Rocquencourt, France)

·            Djamé Seddah (Inria Rocquencourt, France)

·            Wolfgang Seeker (IMS Stuttgart, Germany)

·            Anders Soogard (University of Copenhagen, Denmark)

·            Reut Tsarfaty (Uppsala University, Sweden)

·            Lamia Tounsi (Dublin City University, Ireland)

·            Daniel Zeman (Charles University, Czechia)



*Contact*

For up-to-date information, please visit
http://www.spmrl.org/spmrl-sancl2014.html.

For general questions about the workshop, please email spmrl.sancl at gmail.com.
For specific questions about the shared task, please email the shared task
organizers spmrl.sharedtask at gmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://list.hum.uu.nl/pipermail/elsnet-list/attachments/20140312/6e40826c/attachment-0001.html>


More information about the Elsnet-list mailing list