<html><head><meta http-equiv="Content-Type" content="text/html charset=iso-8859-1"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><div><blockquote type="cite"></blockquote>Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)<br><blockquote type="cite"></blockquote>EMNLP 2014 / SIGMT / SIGLEX Workshop<br><blockquote type="cite"></blockquote>Oct 2014, Doha, Qatar<br><blockquote type="cite"></blockquote><a href="http://www.cse.ust.hk/~dekai/ssst/">http://www.cse.ust.hk/~dekai/ssst/</a><br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>*** Special theme: Compositional Distributional Semantics and Machine Translation ***<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>The Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8) seeks to bring together a large number of researchers working on diverse aspects of structure, semantics and representation in relation to statistical machine translation. Since its first edition in 2006, its program each year has comprised high-quality papers discussing current work spanning topics including: new grammatical models of translation; new learning methods for syntax- and semantics-based models; formal properties of synchronous/transduction grammars (hereafter S/TGs); discriminative training of models incorporating linguistic features; using S/TGs for semantics and generation; and syntax- and semantics-based evaluation of machine translation.<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>We invite two types of submissions this year:<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>1. Extended abstracts for poster or hands-on presentations on the special theme<br><blockquote type="cite"></blockquote>2. Full papers spanning all areas of interest for SSST<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>===========================<br><blockquote type="cite"></blockquote>Special Theme Extended Abstracts<br><blockquote type="cite"></blockquote>===========================<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>This year, the special theme of semantics of the past three editions of SSST takes a new step with a "working workshop" bringing together researchers interested in compositional distributional semantics, distributed representations, and continuous vector space models in MT, with tutorials bridging both directions, as well as discussions and hands-on work on relevant tasks with real data. Such models have proven beneficial for a number of NLP tasks, for example phrasal similarity, lexical entailment, modeling semantic deviance, detecting order restrictions in recursive structures, or improving NP bracketing in parsing. However, they have not received as much attention in MT.<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>Extended abstracts of at most two (2) pages should describe poster or hands-on presentations that will stimulate discussions on the special theme of compositional distributional semantics and machine translation, including position papers, recent work, pilot studies, negative results. We encourage the presentation of relevant work that has been published or submitted elsewhere, as well as new work in progress.<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>=========<br><blockquote type="cite"></blockquote>Full Papers<br><blockquote type="cite"></blockquote>=========<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>The need for structural mappings between languages is widely recognized in the fields of statistical machine translation and spoken language translation, and there is now wide consensus that these mappings are appropriately represented using a family of formalisms that includes synchronous/transduction grammars and similar notational equivalents. To date, flat-structured models, such as the word-based IBM models of the early 1990s or the more recent phrase-based models, remain widely used. But tree-structured mappings arguably offer a much greater potential for learning valid generalizations about relationships between languages.<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>Within this area of research there is a rich diversity of approaches. There is active research ranging from formal properties of S/TGs to large-scale end-to-end systems. There are approaches that make heavy use of linguistic theory, and approaches that use little or none. There is theoretical work characterizing the expressiveness and complexity of particular formalisms, as well as empirical work assessing their modeling accuracy and descriptive adequacy across various language pairs. There is work being done to invent better translation models, and work to design better algorithms. Recent years have seen significant progress on all these fronts. In particular, systems based on these formalisms are now top contenders in MT evaluations.<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>At the same time, SMT has seen a movement toward semantics over the past few years, which has been reflected at recent SSST workshops, including the last three editions which had semantics for SMT as a special theme. The issues of deep syntax and shallow semantics are closely linked and SSST-8 continues to encourage submissions on semantics for MT in a number of directions, including semantic role labeling, sense disambiguation, and compositional distributional semantics for translation and evaluation.<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>We invite papers on:<br><blockquote type="cite"></blockquote> syntax-based / semantics-based / tree-structured SMT<br><blockquote type="cite"></blockquote> machine learning techniques for inducing structured translation models<br><blockquote type="cite"></blockquote> algorithms for training, decoding, and scoring with semantic representation structure<br><blockquote type="cite"></blockquote> empirical studies on adequacy and efficiency of formalisms<br><blockquote type="cite"></blockquote> creation and usefulness of syntactic/semantic resources for MT<br><blockquote type="cite"></blockquote> formal properties of synchronous/transduction grammars<br><blockquote type="cite"></blockquote> learning semantic information from monolingual, parallel or comparable corpora<br><blockquote type="cite"></blockquote> unsupervised and semi-supervised word sense induction and disambiguation methods for MT<br><blockquote type="cite"></blockquote> lexical substitution, word sense induction and disambiguation, semantic role labeling, textual entailment, paraphrase and other semantic tasks for MT<br><blockquote type="cite"></blockquote> semantic features for MT models (word alignment, translation lexicons, language models, etc.)<br><blockquote type="cite"></blockquote> evaluation of syntactic/semantic components within MT (task-based evaluation)<br><blockquote type="cite"></blockquote> scalability of structured translation methods to small or large data<br><blockquote type="cite"></blockquote> applications of S/TGs to related areas including:<br><blockquote type="cite"></blockquote> speech translation<br><blockquote type="cite"></blockquote> formal semantics and semantic parsing<br><blockquote type="cite"></blockquote> paraphrases and textual entailment<br><blockquote type="cite"></blockquote> information retrieval and extraction<br><blockquote type="cite"></blockquote> syntactically- and semantically-motivated evaluation of MT<br><blockquote type="cite"></blockquote> compositional distributional semantics in MT<br><blockquote type="cite"></blockquote> distributed representations and continuous vector space models in MT<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>=========<br><blockquote type="cite"></blockquote>Organizers<br><blockquote type="cite"></blockquote>=========<br><blockquote type="cite"></blockquote>Dekai WU, Hong Kong University of Science and Technology (HKUST)<br><blockquote type="cite"></blockquote>Marine CARPUAT, National Research Council (NRC) Canada<br><blockquote type="cite"></blockquote>Xavier CARRERAS, Universitat Politècnica de Catalunya (UPC)<br><blockquote type="cite"></blockquote>Eva Maria VECCHI, Cambridge University<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>=============<br><blockquote type="cite"></blockquote>Important Dates<br><blockquote type="cite"></blockquote>=============<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>Submission deadline for papers and extended abstracts: <b>26 Jul 2014</b><br><blockquote type="cite"></blockquote>Notification to authors: 26 Aug 2014<br><blockquote type="cite"></blockquote>Camera copy deadline: 15 Sep 2014<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote>For more information<br><blockquote type="cite"></blockquote>http://www.cse.ust.hk/~dekai/ssst/<br><blockquote type="cite"></blockquote><font color="#0f61c8"><br></font><blockquote type="cite"></blockquote></div><br></body></html>