<html dir="ltr">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<style type="text/css" id="owaParaStyle"></style>
</head>
<body fpstyle="1" ocsi="0">
<div style="direction: ltr;font-family: Tahoma;color: #000000;font-size: 10pt;">
<div>== The 2nd Workshop on Noisy User-generated Text (WNUT'16) ==</div>
<div><br>
</div>
<div><br>
</div>
<div>The WNUT Workshop will be held with COLING in Osaka, Japan, on December 11, 2016. The website for the workshop is at: </div>
<div><br>
</div>
<div>http://noisy-text.github.io/</div>
<div><br>
</div>
<div><br>
</div>
<div>WNUT workshop focuses on Natural Language Processing applied to noisy user-generated text, such as that found in social media, web forums, online reviews, clinic records and language learner essays. This year, there will be two *shared tasks*: 1) Geolocation
Prediction in Twitter and 2) Named Entity Recognition in Twitter.</div>
<div><br>
</div>
<div><br>
</div>
<div>We seek submissions of both long and short papers on original and unpublished work (same page limit as COLING main conference). 1-page abstracts on work-in-progress or work published elsewhere are also welcome and will *not* be included in the conference
proceedings. All accepted submissions will be presented as posters. Additionally, selected submissions will be presented orally. </div>
<div><br>
</div>
<div><br>
</div>
<div>Topics of interest include but are not limited to:</div>
<div><br>
</div>
<div>* NLP Preprocessing of Noisy Text</div>
<div> - Part of speech tagging</div>
<div> - Named entity tagging, including a wide range of categories, e.g. product names</div>
<div> - Chunking of user-generated text</div>
<div> - Parsing</div>
<div>* Text Normalization and Error Correction</div>
<div> - Normalizing noisy text for downstream tasks and for human readability</div>
<div> - Error detection and correction</div>
<div>* Paraphrase extraction and detection in noisy text</div>
<div>* User prediction, e.g. geolocation, gender, age, etc</div>
<div>* Bilingual translation of noisy text</div>
<div>* Multilingual NLP in noisy text</div>
<div>* Colloquial language, e.g. idiom detection</div>
<div>* Domain adaptation to user-generated text</div>
<div>* Geolocation prediction</div>
<div>* Global and regional trend detection and event extraction</div>
<div>* Extracting user demographics, profiles and major life events</div>
<div>* Detecting rumors and contradictory information on social media</div>
<div>* Temporal aspects of user-generated content (resolving time expressions, concept drift, diachronic analyses, etc...)</div>
<div><br>
</div>
<div><br>
</div>
<div><br>
</div>
<div>= IMPORTANT DATES =</div>
<div><br>
</div>
<div>* January 24 2015: First call for workshop papers</div>
<div>* September 2016: Shared-task evaluations</div>
<div>* September 25, 2016: Workshop paper due</div>
<div>* October 16, 2016: Notification of acceptance</div>
<div>* October 30, 2016: Camera-ready papers due</div>
<div>* December 11, 2016: Workshop date</div>
<div><br>
</div>
<div><br>
</div>
<div>= SHARED TASKS = </div>
<div><br>
</div>
<div>* Task #1: Geolocation Prediction in Twitter (September 18, 2016)</div>
<div>* Task #2: Named Entity Recognition in Twitter (September 9-16, 2016 )</div>
<div><br>
</div>
<div><br>
</div>
<div>= ORGANIZERS =</div>
<div><br>
</div>
<div>Bo Han (Hugo AI)</div>
<div>Alan Ritter (The Ohio State University)</div>
<div>Leon Derczynski (The University of Sheffield)</div>
<div>Wei Xu (The Ohio State University)</div>
<div>Tim Baldwin (The University of Melbourne)</div>
<div><br>
</div>
<div><br>
</div>
<div>= INVITED SPEAKERS =</div>
<div><br>
</div>
<div>Ming-Wei Chang (Microsoft Research)</div>
<div>Barbara Plank (University of Groningen)</div>
<div>Kentaro Torisawa (National Institute of Information and Communications Technology)</div>
<div><br>
</div>
<div><br>
</div>
<div>= PROGRAM COMMITTEE =</div>
<div><br>
</div>
<div>David Bamman (University of California, Berkeley)</div>
<div>Kalina Bontcheva (University of Sheffield)</div>
<div>Claire Cardie (Cornell University)</div>
<div>Colin Cherry (National Research Council Canada)</div>
<div>Grzegorz Chrupała (Tilburg University)</div>
<div>Marina Danilevsky (IBM Research)</div>
<div>Seza Doğruöz (Tilburg University)</div>
<div>Heba Elfardy (Columbia University)</div>
<div>Eric Fosler-Lussier (The Ohio State University)</div>
<div>Kevin Gimpel (Toyota Technological Institute at Chicago)</div>
<div>Weiwei Guo (Yahoo! Research)</div>
<div>Ben Hachey (Hugo AI)</div>
<div>Masato Hagiwara (Duolingo)</div>
<div>Ed Hovy (Carnegie Mellon University)</div>
<div>Jing Jiang (Singapore Management University)</div>
<div>Nobuhiro Kaji (Yahoo! Research)</div>
<div>Emre Kiciman (Microsoft Research)</div>
<div>Chen Li (University of Texas at Dallas)</div>
<div>Wang Ling (Google DeepMind)</div>
<div>Huan Liu (Arizona State University)</div>
<div>Rada Mihalcea (University of Michigan)</div>
<div>Smaranda Muresan (Columbia University)</div>
<div>Preslav Nakov (Qatar Computing Research Institute)</div>
<div>Naoaki Okazaki (Tohoku University)</div>
<div>Miles Osborne (Bloomberg)</div>
<div>Ellie Pavlick (University of Pennsylvania)</div>
<div>Daniel Preoţiuc-Pietro (University of Pennsylvania)</div>
<div>Will Radford (Hugo AI)</div>
<div>Shourya Roy (Xerox Research)</div>
<div>Alla Rozovskaya (City University of New York)</div>
<div>Andrew Schwartz (Stony Brook University)</div>
<div>Djamé Seddah (University Paris-Sorbonne)</div>
<div>Richard Sproat (Google Research)</div>
<div>Anders Søgaard (University of Copenhagen)</div>
<div>Jeniya Tabassum (The Ohio State University)</div>
<div>Joel Tetreault (Yahoo! Research)</div>
<div>Byron C. Wallace (University of Texas at Austin)</div>
<div>Svitlana Volkova (Pacific Northwest National Laboratory)</div>
<div>Xiaojun Wan (Peking University)</div>
<div>Jun-Ming Xu (University of Wisconsin-Madison)</div>
<div>Diyi Yang (Carnegie Mellon University)</div>
<div>Yi Yang (Georgia Tech)</div>
<div>Guido Zarrella (MITRE)</div>
<div>Ming Zhou (Microsoft Research)</div>
<div><br>
</div>
<div><br>
</div>
<div>= SUBMISSION =</div>
<div><br>
</div>
<div>Formatting should be according to COLING 2016 specifications.</div>
<div>Dual submission is allowed, but must state at the time of submission.</div>
<div><br>
</div>
<div>Please submit through the START system at the following url:</div>
<div><br>
</div>
<div>https://www.softconf.com/coling2016/WNUT/</div>
</div>
</body>
</html>