<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><br><div><br>** Apologies for multiple postings **<br><br><br>======================================================================<br>SECOND CALL FOR PAPERS <br>------------------------------------------<div>ACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing<br>of Morphologically-Rich Languages (SP-Sem-MRL)<br>(<a href="http://sites.google.com/site/spsemmrl2012/">http://sites.google.com/site/spsemmrl2012/</a>)<br><br>Endorsed by SIGLEX & SIGPARSE<br>======================================================================<br><br><br></div><div>IMPORTANT DATES<br>-----------------------------</div><div><br>Submission deadline: Mar 31, 2012<br>Notification to authors: Apr 19, 2012<br>Camera-ready deadline: Apr 30, 2012<br>Workshop dates: TBD, during the ACL-2012 workshop period (Jul 12-14, 2012)<br><br></div><div><br>WORKSHOP SCOPE<br>-----------------------------</div><div><br>Morphologically Rich Languages (MRLs) are languages in which<br>grammatical relations such as Subject, Predicate, Object, etc., are<br>indicated morphologically (e.g. through inflection) instead of<br>positionally (as in, e.g. English), and the position of words and<br>phrases in the sentence may vary substantially. The tight connection<br>between the morphology of words and the grammatical relations between<br>them, and the looser connection between the position and grouping of<br>words to their syntactic roles, pose serious challenges for syntactic<br>and semantic processing. Furthermore, since grammatical relations<br>provide the interface to compositional semantics, morphosyntactic<br>phenomena may significantly complicate processing the syntax-semantics<br>interface. In statistical parsing, which has been a cornerstone of<br>research in NLP and had seen great advances due to the widespread<br>availability of syntactically annotated corpora, English parsing<br>performance has reached a high plateau in certain genres, which is<br>however not always indicative of parsing performance in MRLs,<br>dependency-based and constituency-based alike. Semantic processing of<br>natural language has similarly seen much progress in recent years.<br>However, as in parsing, the bulk of the work has concentrated on<br>English, and MRLs may present processing challenges that the community<br>is as of yet unaware of, and which current semantic processing<br>technologies may have difficulty coping with. These challenges may<br>lurk in areas where parses may be used as input, such as semantic role<br>labeling, distributional semantics, paraphrasing and textual<br>entailment, or where inadequate pre-processing of morphological<br>variation hurts parsing and semantic tasks alike.<br><br>This joint workshop aims to build upon the first and second SPMRL<br>workshops (at NAACL-HLT 2010 and IWPT 2011, respectively) while<br>extending the overall scope to include semantic processing where MRLs<br>pose challenges for algorithms or models initially designed to process<br>English. In particular, we seek to explore the use of newly available<br>syntactically and/or semantically annotated corpora, or data sets for<br>semantic evaluation that can contribute to our understanding of the<br>difficulty that such phenomena pose. One goal of this workshop is to<br>encourage cross-fertilization among researchers working on different<br>languages and among those working on different levels of processing.<br>Of particular interest is work addressing the lexical sparseness and<br>out-of-vocabulary issues that occur in both syntactic and semantic<br>processing.<br><br>The workshop will be organised around three broad themes:<br><br>- Syntactic Models: Models and architectures that explicitly integrate<br>morphological analysis and parsing; Cross-language and cross-model<br>comparison of strengths and weaknesses regarding particular linguistic<br>phenomena.<br><br>- Semantic Models: State-of-the-art semantic analysis and generation<br>methods for MRLs, including semantic similarity and entailment<br>criteria and their task-specific instantiation, and suitable<br>representations for semantic tasks in MRLs.<br><br>- Joint Modeling Aspects: Improving lexical coverage and handling of<br>out-of-vocabulary (OOV) words by utilising lexical knowledge or<br>unsupervised/semi-supervised learning techniques; The role of parsing<br>in semantic analysis for MRLs; Preprocessing issues that jointly<br>affect parsing and semantic analysis; Syntax-Semantics interfaces for<br>monolingual or multilingual systems.<br><br>The areas of interest for this joint workshop include, but are not<br>limited to, the following topics:<br><br>--Syntactic Parsing of MRLs</div><div><br>* parsing models and architectures that explicitly integrate<br><span class="Apple-tab-span" style="white-space: pre; "> </span>morphological analysis and parsing<br>* parsing models and architectures that focus on lexical coverage<br><span class="Apple-tab-span" style="white-space: pre; "> </span>and the handling of OOV words either by incorporating linguistic<br><span class="Apple-tab-span" style="white-space: pre; "> </span>knowledge or through the use of unsupervised/semi-supervised learning<br><span class="Apple-tab-span" style="white-space: pre; "> </span>techniques<br>* Cross-language and cross-model comparison of models' strengths<br><span class="Apple-tab-span" style="white-space: pre; "> </span>and weaknesses in the face of particular linguistic phenomena (e.g.<br><span class="Apple-tab-span" style="white-space: pre; "> </span>morphosyntactic characteristics, degree of word-order freedom)<br>* Comprehensive analyses of the strengths and weaknesses of various<br><span class="Apple-tab-span" style="white-space: pre; "> </span>parsing models on particular linguistic (e.g. morphosyntactic)<br><span class="Apple-tab-span" style="white-space: pre; "> </span>phenomena with respect to variation in tagsets, annotation schemes and<br><span class="Apple-tab-span" style="white-space: pre; "> </span>additional data transformations<br><br></div><div><br>--Semantic Processing of MRLs<br><br>* Semantic distance and entailment criteria in the MRL space (e.g.,<br><span class="Apple-tab-span" style="white-space: pre; "> </span>with respect to inflection, derivation, root, pattern, lemma, tense,<br><span class="Apple-tab-span" style="white-space: pre; "> </span>and/or aspect, etc.); possibly task-specific criteria<br>* Lexical resources and morphological analysis tools facilitating<br><span class="Apple-tab-span" style="white-space: pre; "> </span>semantic distance measures and semantic relation detection<br>* Methods and models for semantic similarity/distance calculation,<br><span class="Apple-tab-span" style="white-space: pre; "> </span>clustering and paraphrasing relying on MRL properties, and using:<br><span class="Apple-tab-span" style="white-space: pre; "> </span>probability, vector/graph representation, data-driven and/or<br><span class="Apple-tab-span" style="white-space: pre; "> </span>linguistic rules, pivoting/SMT, machine-learning, etc.<br>* Paraphrase and textual entailment detection or generation,<br><span class="Apple-tab-span" style="white-space: pre; "> </span>specific to MRLs (e.g., task-specific issues of inclusion or exclusion<br><span class="Apple-tab-span" style="white-space: pre; "> </span>of certain paraphrase and textual entailment patterns differing in<br><span class="Apple-tab-span" style="white-space: pre; "> </span>inflection)<br>* Use of morphological analysis for semantic calculation aimed at<br><span class="Apple-tab-span" style="white-space: pre; "> </span>reducing sparsity / OOV rate, preferably without losing information<br><span class="Apple-tab-span" style="white-space: pre; "> </span>due to mere lemmatization<br>* Semantic role labeling (SRL) for MRLs; verbal/nominalized<br><span class="Apple-tab-span" style="white-space: pre; "> </span>selectional preferences<br><br><br>--The Syntax-Semantics Interface:<br><br>* Parsing-based semantic processing tasks, e.g., semantic role<br><span class="Apple-tab-span" style="white-space: pre; "> </span>labeling (SRL)<br>* Processing of compounds and multi-morphemic words: optimal<br><span class="Apple-tab-span" style="white-space: pre; "> </span>level(s) of tokenization, representation, and morphological analysis<br><span class="Apple-tab-span" style="white-space: pre; "> </span>for either/both tasks<br>* Syntax-aware semantic distance measures, paraphrasing and textual<br><span class="Apple-tab-span" style="white-space: pre; "> </span>entailment<br>* Semantic classes and/or relations as input to syntactic parsing<br><br><br>In addition to the standard (oral or poster) presentations in the<br>sessions, the SP-Sem-MRL workshop will feature a panel of commentators<br>for a selection of the talks, allowing for an extended discussion<br>period. This new feature is introduced in order to foster in-depth<br>discussions and to nurture interactions among researchers. It is our<br>hope that these interactions will help to bring ideas (and solutions)<br>to the fore and promote a more rapid advance of the state-of-the-art<br>in the field.<br><br><div><br>Shared Task<br>------------------<br><br>There will be no shared task on MRLs this year. However, we will take<br>this opportunity to disclose, during a special session of SP-Sem-MRL,<br>the data sets and evaluation procedures for the cross-linguistic<br>cross-framework shared task which was discussed at previous SPMRL<br>panels, and which is planned for SPMRL 2013 at IWPT 2013. Researchers<br>who are interested in participating in the shared task or teams that<br>wish to add their data sets or extrinsic evaluation procedures to the<br>task are encouraged to attend the session and contribute to the<br>discussion.<br><br><br>SUBMISSION<br>-------------------<br><br>Authors are invited to submit long papers (up to 10 pages + any number<br>of reference pages) and short papers (up to 5 pages + any number of<br>reference pages). Long papers should describe unpublished, substantial<br>and completed research. Short papers should be position papers, papers<br>describing work in progress or short, focused contributions.<br><br>Papers may be submitted until 31 March 2012 in PDF format via the START system:<br><br><a href="https://www.softconf.com/acl2012/sp-sem-mrl-2012/">https://www.softconf.com/acl2012/sp-sem-mrl-2012/</a><br><br>Submitted papers must follow the styles and the formatting guidelines<br>available from the current ACL recommendations<br>(<a href="http://www.acl2012.org/call/sub01.asp">http://www.acl2012.org/call/sub01.asp</a>). As the reviewing will be<br>blind, the papers must not include the authors' names and<br>affiliations. Furthermore, self-references that reveal the author's<br>identity, e.g., "We previously showed (Smith, 1991) ..." must be<br>avoided. Instead, use citations such as "Smith previously showed<br>(Smith, 1991) ..." Papers that do not conform to these requirements<br>will be rejected without review. In addition, please do not post your<br>submissions on the web until after the review process is complete.<br><br><br>ORGANIZING COMMITTEE<br>--------------------------------------<br><br>General chairs:<br>Marianna Apidianaki (LIMSI-CNRS, France)<br>Ido Dagan (Bar-Ilan University, Israel)<br>Jennifer Foster (Dublin City University, Ireland)<br>Yuval Marton (IBM Watson Research Center, US)<br>Djamé Seddah (University of Paris 4, France)<br>Reut Tsarfaty (Uppsala University, Sweden)<br><br>Shared session chairs:<br>Katrin Erk (University of Texas at Austin, US)<br>Ines Rehbein (University of Potsdam, Germany)<br>Peter Turney (National Research Council, Canada)<br>Yannick Versley (University of Tuebingen, Germany)<br><br></div><div><br>PROGRAM COMMITTEE<br>-----------------------------------</div><div><br>Ion Androutsopoulos (Athens University of Economics and Business, Greece)<br>Mohammed Attia (Dublin City University, Ireland)<br>Bernd Bohnet (University of Stuttgart, Germany)<br>Marie Candito (University of Paris 7, France)<br>Aoife Cahill (Educational Testing Service, US)<br>Ozlem Cetinoglu (University of Stuttgart, Germany)<br>Jinho Choi (University of Colorado at Boulder, US)<br>Grzegorz Chrupala (Saarland University, Germany)<br>Benoit Crabbé (University of Paris 7, France)<br>Gülşen Cebiroğlu Eryiğit, (Istanbul Technical University, Turkey)<br>Josef van Genabith (Dublin City University, Ireland)<br>Yoav Goldberg (Google Research NY, US)<br>Spence Green (Stanford University, US)<br>Veronique Hoste (University College Ghent, Belgium)<br>Samar Husain (Potsdam University, Germany)<br>Sandra Kübler (Indiana University, US)<br>Jonas Kuhn (University of Stuttgart, Germany)<br>Mirella Lapata (University of Edinburgh, UK)<br>Alberto Lavelli (FBK-irst, Italy)<br>Alessandro Lenci (University of Pisa, Italy)<br>Joseph Le Roux (Université Paris-Nord, France)<br>Nitin Madnani (Educational Testing Service, NJ)<br>Wolfgang Maier (University of Düsseldorf, Germany)<br>Takuya Matsuzaki (University of Tokyo, Japan)<br>Aurélien Max (LIMSI-CNRS, France)<br>Yusuke Miyao (University of Tokyo, Japan)<br>Preslav Nakov (Qatar Computing Research Institute, Qatar)<br>Roberto Navigli (Sapienza University of Rome, Italy)<br>Kemal Oflazer (Carnegie Mellon University, Qatar)<br>Sebastian Pado (University of Heidelberg, Germany)<br>Patrick Pantel (Microsoft Research, US)<br>Sameer Pradhan (BBN Technologies, US)<br>Idan Szpektor (Bar-Ilan University, Israel)<br>Kenji Sagae (University of Southern California, US)<br>Benoit Sagot (INRIA Rocquencourt, France)<br>Lamia Tounsi (Dublin City University, Ireland)<br>Tim Van de Cruys (University of Cambridge, UK)<br>Stephen Wan (CSIRO ICT Centre, Sydney)<br>Deniz Yuret (Koc University Istanbul, Turkey)<br>Zdenek Zabokrtsky (Charles University, Czech Republic)<br>Shiqi Zhao (Baidu Inc., China)<br><br><br>CONTACT<br>---------------<br>e-mail: <a href="mailto:sp.sem.mrl2012@gmail.com">sp.sem.mrl2012@gmail.com</a><br>website: <a href="https://sites.google.com/site/spsemmrl2012/">https://sites.google.com/site/spsemmrl2012/</a><br><br><br>SPONSORS<br>-----------------<br>This workshop is endorsed by SIGLEX and SIGPARSE, and<br>sponsored by INRIA's Alpage project.<br><br>======================================================================<br></div></div></div><div><br></div><div><br></div><div><br></div><br><br><div apple-content-edited="true"> <span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; font-size: medium; "><div><br class="Apple-interchange-newline">Marianna Apidianaki</div><div>CNRS Researcher</div><div>LIMSI, Orsay</div><div><a href="http://www.limsi.fr/~marianna">www.limsi.fr/~marianna</a></div></span> </div><br></body></html>