LINGUIST List 23.62|
Wed Jan 04 2012
Calls: Computational Ling, Text/Corpus Ling/Turkey
Editor for this issue: Alison Zaharee
LINGUIST is pleased to announce the launch of an exciting new feature: Easy Abstracts! Easy Abs is a free abstract submission and review facility designed to help conference organizers and reviewers accept and process abstracts online. Just go to: http://www.linguistlist.org/confcustom, and begin your conference customization process today! With Easy Abstracts, submission and review will be as easy as 1-2-3!
1. Martí Quixal ,
NLP can u tag #user_gene?!
Message 1: NLP can u tag #user_gene?!
From: Martí Quixal <marti.quixalbarcelonamedia.org>
Subject: NLP can u tag #user_gene?!
E-mail this message to a friend
Full Title: NLP can u tag #user_gene?!
Short Title: NLP4UGC 2012
Date: 26-May-2012 - 26-May-2012
Location: Istanbul, Turkey
Contact Person: Maite Melero
Meeting Email: < click here to access email >
Web Site: http://nlp4ugc.barcelonamedia.org/Site/Welcome.html
Linguistic Field(s): Computational Linguistics; Text/Corpus Linguistics
Call Deadline: 15-Feb-2012
NLP4UGC 2012: NLP can u tag #user_gene?! via lrec-conf.org
Workshop in conjunction with LREC 2012
Istanbul, May 21 - 27 2012
Workshop date: Saturday May 26 2012 (afternoon)
The Web 2.0 has transferred the authorship of contents from institutions to the people; the web has become a channel where users exchange, explain or write about their lives and interests, give opinions and rate others' opinions. The so-called User Generated Content (UGC) in text form is a valuable resource that can be exploited for many purposes, such as cross-lingual information retrieval, opinion mining, enhanced web search, social science analysis, intelligent advertising, and so on.
In order to mine the data from the Web 2.0 we first need to understand its contents. Analysis of UG content is challenging because of its casual language, with plenty of abbreviations, slang, domain specific terms and, compared to published edited text, with a higher rate of spelling and grammar errors. Standard NLP techniques, which are used to analyze text and provide formal representations of surface data, have been typically developed to deal with standard language and may not yield the expected results on UGC. For example, shortened or misspelled words, which are very frequent in the Web 2.0 informal style, increase the variability in the forms for expressing a single concept.
This workshop aims at providing a meeting point for researchers working in the processing of UGC in textual form in one way or another, as well as developers of UGC-based applications and technologies, both from industry and academia.
Call for Papers:
Topics of Interest:
We are mainly interested in, but not restricted to, the following research questions:
- What characterises UGC? Linguistic and textual phenomena that distinguish UGC from standard written text, and may pose a challenge for NLP
- Definition of norm, concept of error, deviation and variation in UGC
- Criteria and standards for the annotation of evaluation corpora in UGC at various levels of linguistic analysis (form, part of speech, constituents, dependencies, speech acts, deviation types, etc.)
- How quality of text affects processing tasks (tokenization, POS tagging, chunking, parsing, named-entity detection, etc.)
- Architecture and software design for flexible adaptation of NLP processing pipelines to new domains (topic domains and text-genre domains)
- Text normalisation vs adaptation of processing tools:
Pros and cons
Costs and benefits
- Approaches to normalisation (text checking, ASR, MT techniques, etc.)
- Evaluation issues related to processing and normalising UGC
The workshop aims at bringing together researchers and developers from academia and industry. In particular, perspectives from the following user groups are welcome:
- UGC-based application developers, from both research and industry
- Researchers from the NLP, IR and IE communities
- PhD students interested or working in the processing of UGC
Oral papers and posters should follow the main conference formatting requirements (http://www.lrec-conf.org/lrec2012/).
To submit contributions, please follow the instructions at:
The contributions will undergo a double review by members of the programme committee. When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. For further information on this new initiative, please refer to:
February 15, 2012: Paper submission deadline
March 15, 2012: Acceptance notifications
March 30, 2012: Camera-ready papers
May 26, 2012: Afternoon workshop at LREC
Laura Alonso i Alemany, Universidad Nacional de Córdoba (Argentina)
Jordi Atserias, Yahoo! Research (Spain)
Toni Badia, Universitat Pompeu Fabra (Spain)
Maite Melero, Barcelona Media Innovation Center (Spain)
Martí Quixal, Barcelona Media Innovation Center (Spain)
Rafael Banchs, Institute for Infocomm Research - A*Star (Singapore)
Steven Bedrick, Oregon Health & Science University
Richard Beaufort, Cental, Catholic University of Louvain (Belgium)
Joan Codina, Universitat Pompeu Fabra (Spain)
Louise-Amélie Cougnon, Cental, Université Catholique de Louvain (Belgium)
Jennifer Foster, Dublin City University (Ireland)
Michael Gamon, Microsoft Research (USA)
Dan Lopresti, CS&E, Lehigh University (USA)
Fei Liu, Bosch Research (USA)
Ulrike Pado, VICO Research&Consulting GmbH (Germany)
Lluís Padró, Universitat Politècnica de Catalunya (Spain)
Alan Ritter, CSE, University of Washington (USA)
Roser Saurí, Barcelona Media Innovation Center (Spain)
Paul Schmidt, Institut für Angewandten Informationsforschung (Germany)
L. Venkata Subramaniam, IBM Research (India)
Read more issues|LINGUIST home page|Top of issue
Page Updated: 04-Jan-2012
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.