Outline

The SPMRL series of workshop provides a forum for research in parsing morphologically-rich languages, with the goal of identifying cross-cutting issues in the annotation and parsing methodology for such languages, which typically have more flexible word order and/or higher word-form variation than English.

What we have learned

Past SPMRL installments have been host to successful identification of some problem areas and approaches that address these problems: in the presence of word order variation, more meaningful results can be reached through treebank transformations (Versley & Rehbein 2009; Tsarfaty & Sima'an 2010, Choi et al., 2012) or latent annotations (Petrov et al., 2006), the parallel use of constituency and dependency structures (Le Roux et al., 2012), as well as techniques to provide prior knowledge in the handling of unseen words (Candito & Seddah 2010, Rehbein 2011, Sigogne et al 2011; Anguiano & Candito 2012).

SPMRL has also been host to discussions on realistic and appropriate evaluation methods that can be applied in the face of morphological and/or segmentation ambiguities; these discussions have culminated in a shared task for parsing these morphologically-rich languages, which will be co-located with the workshop.

Areas of interest

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

• applying cutting-edge parsing techniques to new languages
• strengths and weaknesses of current parsing techniques when applied to morphologically-rich languages
• insights and techniques that are targeted at improving parsing quality for morphologically-rich languages
• using insights from parsing and associated processing problems to motivate decisions in the creation of new syntactically annotated corpora
• annotation and parsing of data from domains and genres that are not yet covered for many languages

Important Dates

(NEW: Submission deadline has been moved from July 5th to July 29th)

How to Submit

Authors are invited to submit long papers (up to 9 pages + references) and short papers (up to 5 pages + references). Long papers should describe unpublished, substantial and completed research. Short papers should be position papers, papers describing work in progress or short, focused contributions.

Submissions will be accepted until July, 29 , 2013, (11:59 p.m. PST) in PDF format via the START system and must be formatted using the NAACL 2013 stylefiles.

Organizers

Program committee

• Mohammed Attia (Dublin City University, Ireland)
• Bernd Bohnet (University of Birmingham, UK)
• Marie Candito (University of Paris 7, France)
• Aoife Cahill (Educational Testing Service Inc., US)
• Ozlem Cetinoglu (University of Stuttgart, Germany)
• Jinho Choi (IPSoft Inc., US)
• Grzegorz Chrupala (Tilburg University, Netherlands)
• Benoit Crabbé (University of Paris 7, France)
• Gülsen Cebiroglu Eryigit (Istanbul Technical University, Turkey)
• Michael Elhadad (Ben Gurion University, Israel)
• Richard Farkas (University of Szeged, Hungary)
• Jennifer Foster (Dublin City University, Ireland)
• Josef van Genabith (Dublin City University, Ireland)
• Koldo Gojenola (University of the Basque Country, Spain)
• Spence Green (Stanford University, US)
• Samar Husain (Potsdam University, Germany)
• Sandra Kübler (Indiana University, US)
• Jonas Kuhn (University of Stuttgart, Germany)
• Alberto Lavelli (FBK-irst, Italy)
• Joseph Le Roux (Université Paris-Nord, France)
• Wolfgang Maier (University of Düsseldorf, Germany)
• Takuya Matsuzaki (University of Tokyo, Japan)
• 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)
• Reut Tsarfaty (Uppsala University, Sweden)
• Lamia Tounsi (Dublin City University, Ireland)
• Daniel Zeman (Charles University, Czechia)

ENDORSEMENT

This workshop is endorsed by THE ACL SIGPARSE interest group.

For their precious help preparing the SPMRL 2013 Shared Task and for allowing their data to be part of it, we warmly thank the Linguistic Data Consortium, the Knowledge Center for Processing Hebrew (MILA), the Ben Gurion University, Columbia University, Institute of Computer Science (Polish Academy of Sciences), Korea Advanced Institute of Science and Technology, University of the Basque Country, University of Lisbon, Uppsala University, University of Stuttgart, University of Szeged and University Paris Diderot (Paris 7).