<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
<div> ACL 2008</div><div> WORKSHOP ON PARSING GERMAN</div><div> (PaGe 08)</div><div> June 20, 2008</div><div> Columbus, Ohio</div><div><br class="webkit-block-placeholder"></div><div> <a href="http://www.cs.toronto.edu/acl08parsinggerman/">http://www.cs.toronto.edu/acl08parsinggerman/</a></div><div><br class="webkit-block-placeholder"></div><div> FINAL CALL FOR PAPERS</div><div><span class="Apple-tab-span" style="white-space:pre"> </span>***** EXTENDED DEADLINE: March 24*****</div><div><br class="webkit-block-placeholder"></div><div>German possesses an interesting set of configurational properties on</div><div>the syntactic level which make it far less flexible with respect to</div><div>word order than other free word order languages. Analyses of these</div><div>properties, which have formed a part of the traditional syntax of</div><div>German since the early 19th century, only re-entered the mainstream of</div><div>generative linguistics research within the last twenty years or so.</div><div>In computational linguistics, however, their realization has varied</div><div>quite widely: "topological fields" in HPSG-style analyses, multiple</div><div>parse trees, special constraints on liberation in constraint-based</div><div>dependency-style analyses, various hybrid "deep/shallow" approaches,</div><div>and agnostic parameter estimation over graphs. This variation can</div><div>also acutely be felt in the annotation of German treebanks. Many</div><div>corpora have historically elected to annotate only a few of the</div><div>different senses of the term "constituent" inherent to German syntax,</div><div>resulting in standards that make German appear either more like</div><div>English or more like Czech.</div><div><br class="webkit-block-placeholder"></div><div>The aim of this workshop is to provide a forum for theoretical</div><div>discussion as well as a shared task, based on the TIGER and TueBa-D/Z</div><div>German treebanks, for these various approaches to make their case on</div><div>empirical grounds. This combination we believe to be essential to</div><div>balancing the considerations of what structure merits learning versus</div><div>the ease with which it can be learned. Both treebanks are annotated</div><div>collections of German newspaper text on similar topics. They are</div><div>annotated with POS, morphology, phrase structure, and grammatical</div><div>functions. TueBa-D/Z additionally uses topological fields to describe</div><div>fundamental word order restrictions in German clauses. The treebanks</div><div>differ significantly in their annotation schemes, however: while TIGER</div><div>relies on crossing branches to describe long distance relationships,</div><div>TueBa-D/Z uses pure tree structures with designated labels for long</div><div>distance relationships. Additionally, the annotation is TIGER is flat</div><div>on the phrasal level while TueBa-D/Z annotates phrasal structure more</div><div>hierarchically.</div><div><br class="webkit-block-placeholder"></div><div>*Participation in the shared task is optional*.</div><div><br class="webkit-block-placeholder"></div><div>TOPICS</div><div><br class="webkit-block-placeholder"></div><div>* constituent based approaches to parsing German</div><div>* dependency based approaches to parsing German</div><div>* treatment of long-distance relationships in German</div><div>* comparisons of parsing results for German to other free word order languages</div><div><br class="webkit-block-placeholder"></div><div>SHARED TASK</div><div><br class="webkit-block-placeholder"></div><div>The workshop will feature a shared task on parsing German. We will</div><div>provide the following data sets:</div><div><br class="webkit-block-placeholder"></div><div>* TIGER in constituent structure</div><div>* TIGER in dependency structure</div><div>* TueBa-D/Z in constituent structure</div><div>* TueBa-D/Z in dependency structure</div><div><br class="webkit-block-placeholder"></div><div>The task will be to parse both treebanks using one structural</div><div>encoding. The final ranking of systems will be based on averages</div><div>computed between both treebanks. The data sets will be made available</div><div>free of charge for the shared task, but they do require a license.</div><div><br class="webkit-block-placeholder"></div><div>In order to take part in the shared task, participants should register</div><div>their intent to participate by sending an email to</div><div><a href="mailto:skuebler@indiana.edu">skuebler@indiana.edu</a>. More information will be made available to</div><div>registered participants.</div><div><br class="webkit-block-placeholder"></div><div>IMPORTANT DATES</div><div><br class="webkit-block-placeholder"></div><div>Workshop Paper Submission deadline: March 24, 2008</div><div>Notifications sent to authors: April 4, 2008</div><div>Camera ready due: April 18, 2008</div><div>Workshop Dates: June 20, 2008</div><div><br class="webkit-block-placeholder"></div><div>PAPER SUBMISSION INFORMATION</div><div><br class="webkit-block-placeholder"></div><div>Submissions will consist of regular full papers of max. 8 pages,</div><div>formatted following the ACL 2008 main session guidelines. In addition,</div><div>shared task participants will be invited to submit short papers</div><div>(max. 4 pages) describing their systems and/or their evaluation</div><div>metrics. Both submission and review processes will be handled via the</div><div>START system:</div><div><br class="webkit-block-placeholder"></div><div><a href="https://www.softconf.com/acl08/ACL08-WS11/">https://www.softconf.com/acl08/ACL08-WS11/</a></div><div><br class="webkit-block-placeholder"></div><div>PROGRAM COMMITTEE</div><div><br class="webkit-block-placeholder"></div><div>Berthold Crysmann, Bonn</div><div>Amit Dubey, Edinburgh</div><div>Anette Frank, Heidelberg</div><div>Erhard Hinrichs, Tuebingen</div><div>Julia Hockenmaier, Illinois</div><div>Laura Kallmeyer, Tuebingen</div><div>Frank Keller, Edinburgh</div><div>Sandra Kuebler (co-chair)</div><div>Wolfgang Menzel, Hamburg </div><div>Stefan Mueller, Berlin</div><div>Stephan Oepen, Oslo</div><div>Gerald Penn (co-chair)</div><div>Helmut Schmid, Stuttgart</div><div>Gerold Schneider, Zuerich</div><div>Hans Uszkoreit, Saarbruecken</div><div>Josef van Genabith, Dublin</div><div><br class="webkit-block-placeholder"></div><div>WORKSHOP ORGANIZERS</div><div><br class="webkit-block-placeholder"></div><div>Sandra Kuebler<span class="Apple-tab-span" style="white-space:pre"> </span></div><div>Indiana University</div><div><a href="mailto:skuebler@indiana.edu">skuebler@indiana.edu</a></div><div><br class="webkit-block-placeholder"></div><div>Gerald Penn</div><div>University of Toronto</div><div><a href="mailto:gpenn@cs.toronto.edu">gpenn@cs.toronto.edu</a></div><br> <span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px 0px; color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; text-align: auto; -khtml-text-decorations-in-effect: none; text-indent: 0px; -apple-text-size-adjust: auto; text-transform: none; orphans: 2; white-space: normal; widows: 2; word-spacing: 0px; "><div><br></div></span><div><span class="Apple-style-span" style="border-collapse: separate; border-spacing: 0px 0px; color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; text-align: auto; -khtml-text-decorations-in-effect: none; text-indent: 0px; -apple-text-size-adjust: auto; text-transform: none; orphans: 2; white-space: normal; widows: 2; word-spacing: 0px; "></span> </div><br></body></html>