<html><head><style type="text/css"><!-- DIV {margin:0px;} --></style></head><body><div style="font-family:times new roman, new york, times, serif;font-size:12pt"><div>Multi-source Multilingual Information Extraction and Summarization<br><span> (<a target="_blank" href="http://www-lipn.univ-paris13.fr/%7Epoibeau/mmies.html">http://www-lipn.univ-paris13.fr/~poibeau/mmies.html</a>) </span><br><br> Workshop to be help in conjunction with<br><br><br> *** RANLP 2007 ***<br><br> Borovets -
Bulgaria<br><br><span> <a target="_blank" href="http://www.lml.bas.bg/ranlp2007/">http://www.lml.bas.bg/ranlp2007/</a></span><br><br> *** 26th of September 2007 ***<br><br> First Call for Papers<br><br>Information extraction (IE) and text summarization (TS) are key<br>technologies aiming at extracting relevant information from texts and<br>other sources and presenting the information to the user in condensed<br>forms. Recent years have witnessed an explosion of information, making<br>IE and TS particularly important for the information
society. These<br>technologies, however, face new challenges with the adoption of the Web<br>2.0 paradigm (e.g. blogs, wikis) because of their inherent multi-source<br>nature. These technologies have to deal no longer with isolated texts<br>or single narratives but with large scale repositories, or sources --<br>in one or many languages -- containing a multiplicity of views,<br>opinions, or commentaries on particular topics, entities or events.<br>There is thus a need to adapt and/or develop new techniques to<br>deal with these new phenomena.<br><br><br>Recognising similar information across different sources and/or in<br>different languages is of paramount importance in this multi-source,<br>multi-lingual context, in particular the ability to detect paraphrases<br>in texts is relevant here. In information extraction,
merging<br>information from multiple sources can lead to increased accuracy<br>relative to extraction from single sources. In text summarization,<br>similar facts found across sources can inform sentence scoring<br>algorithms. In question answering, the distribution of answers in<br>similar contexts can inform answer ranking components. In occasions,<br>it is not the similarity of information that matters, but its<br>complementary nature. In a multi-lingual context, information<br>extraction and text summarization can provide solutions for<br>cross-lingual access: key pieces of information can be extracted from<br>different texts in one or
many languages, merged, and then conveyed in<br>many natural languages in concise forms. It is therefore important<br>that the research community addresses the following issues:<br><br>** What methods are appropriate to detect<br>similar/complementary/contradictory information? Are hand-crafted<br>rules and knowledge-rich approaches convenient?<br><br>** What methods are there to tackle cross-document and cross-lingual<br>entity and event coreference?<br><br>** What machine learning approaches are most appropriate for this task<br>supervised/unsupervised/semi-supervised? What type of corpora is<br>required for training and testing?<br><br>** What techniques are appropriate to produce
condensed synthesis of<br>the extracted information? What generation techniques are useful here?<br>What kind of techniques can be used to cross domains and languages?<br><br>** What tools are there to support multi-lingual/multi-source access<br>to information? What solutions are there beyond full document<br>translation to produce cross-lingual summaries?<br><br><br>The objective of the workshop is to bring together researchers and<br>practitioners in the areas of extraction, summarization, and other<br>information access technologies to discuss recent approaches to deal<br>with multi-source and multi-lingual challenges.<br><br>We welcome submission concerning the following topics:<br><br>* Multi-source information extraction<br>* Cross-document Cross-lingual coreference<br>* Opinion mining and synthesis<br>* Multi-lingual information
extraction<br>* Cross-lingual Summarization<br>* Tools to support information fusion<br>* Paraphrase identification and generation<br>* Adaptable IE-based text generation<br><br><br>Important Dates:<br><br>Deadline for submission: *** June 15, 2007 ***<br>Notification of acceptance: July 25, 2007<br>Camera-ready copy due: August 31, 2007<br>Workshop: September 26, 2007<br><br><br>Submission guidelines:<br><br>Submissions should be A4, two-column format and should not exceed<br>seven pages, including cover page, figures, tables and references.<br>Times New Roman 12 font is preferred. The first page should state the<br>title of the paper, the author's name(s), affiliation, surface and<br>email address(es), followed by keywords and an abstract and continue<br>with the first section of your paper. Guidelines for
producing<br>camera-ready versions will be available at the conference web site.<br><br><br>Each paper will be reviewed by up to three members of the program<br>committee. Authors of accepted papers will receive guidelines<br>regarding how to produce camera-ready versions of their papers for<br>inclusion in the proceedings.<br> <br><br>Organization<br><br>Thierry Poibeau (CNRS - LIPN, U. Paris 13 - France)<br>E-mail: Thierry.Poibeau@lipn.univ-paris13.fr<br><br>Horacio Saggion (NLP Group, U. Sheffield - United Kingdom)<br>E-mail: saggion@dcs.shef.ac.uk<br><br><br>Program Committee:<br><br> Sophia Ananiadou (U. Manchester, UK)<br> Roberto Basili (U. Roma Tor Vergata, Italy)<br> Kalina Bontcheva (U. Sheffield, UK)<br> Nathalie Colineau (CSIRO, Australia)<br> Nigel Collier (NII, Japan)<br> Hercules
Dalianis (KTH/Stockholm University, Sweden)<br> Thierry Declerck (DFKI, Germany)<br> Brigitte Grau (LIMSI, France)<br> Kentaro Inui (NAIST, Japan)<br> Min-Yen Kan (National University of Singapore, Singapore)<br> Guy Lapalme (U. Montreal, Canada)<br> Diana Maynard (U. Sheffield, UK)<br> Jean-Luc Minel (CNRS - Modyco, France)<br> Constantin Orasan (University of Wolverhampton, UK)<br> Cecile Paris (CSIRO, Australia)<br> Agnes Sandor (Xerox XRCE, France)<br> Ralf Steinberger (European Commission - Joint Research Centre, Italy)<br> Stan Szpakowicz (University of Ottawa, Canada)<br> Lucy Vanderwende (Microsoft Research, USA)<br> Jose Luis Vicedo (University of Alicante, Spain)<br> Roman Yangarber (University of Helsinki, Finland)<br> Liang Zhou (ISI, USA)<br> Michael Zock (LIF, France)<br><br>Paper Submission:<br><br>Details on how to submit your paper will be announced in
due time. <br></div></div><br>
<hr size="1">
Découvrez une nouvelle façon d'obtenir des réponses à toutes vos questions !
Profitez des connaissances, des opinions et des expériences des internautes sur <a href="http://fr.rd.yahoo.com/evt=42054/*http://fr.answers.yahoo.com">Yahoo! Questions/Réponses</a>.</body></html>