Appel: 4th Workshop on Analytics for Noisy Unstructured Text Data (AND)

[Thierry Hamon]

Date: Mon, 31 May 2010 17:18:24 +0200
From: "Segond, Frederique" <Frederique.Segond at xrce.xerox.com>
Message-ID: <D7C2F074F69C644A840DABBECA2CEA8104388E5A at devoluy.xrce.xeroxlabs.com>
X-url: http://sites.google.com/site/and2010workshop

4th Workshop on

Analytics for Noisy Unstructured Text Data (AND)

in conjunction with 19th ACM International Conference on Information
and Knowledge Management (CIKM)

October 26th, 2010, Toronto, Canada

http://sites.google.com/site/and2010workshop
<http://sites.google.com/site/and2010workshop>


Noisy unstructured text data is ubiquitous and abundant in real-world
situations. Handling noisy text poses new challenges for Information
Extraction (IE), Natural Language Processing (NLP), Information
Retrieval (IR) and Knowledge Management (KM). Special handling of
noise as well as noise-robust IR and KM techniques are essential to
overcome these challenges. As in the case of AND 07, 08 and 09, we
intend that AND 2010 will provide researchers an opportunity to
present their latest results toward addressing these challenges. We
seek papers dealing with all aspects of noisy unstructured text data
and its processing.

 

Topics of Interest (not limited to)

* Methods for detecting and correcting errors in noisy text,

* Information Retrieval from noisy text data,

* Machine learning techniques for information extraction from noisy
  text,

* Rule-based approaches for handling noisy text

* Social network analysis involving noisy data

* Crowd-sourcing methods for dealing with noisy data

* Knowledge Management of noisy text data,

* Automatic classification and clustering of noisy unstructured text
  data,

* Noise-invariant document summarization techniques,

* Text analysis techniques for analysis and mining of on-line
  communication texts such as transcribed calls, web logs, chat logs,
  tweets, microblogs, facebook posts, and email exchanges,

* Business Intelligence (BI) applications dealing with noisy text
  data,

* Document Representation and Content Analysis of noisy text documents

* Interplay between linguistic complexity and uncertainty
  characterizing noisy text data in downstream applications,

* Formal theory on characterization of noise,

* Genre recognition based on the type of noise,

* Characterizing, modeling and accounting for historical language
  change,

* Surveys relating to noisy text analytics

 

Submission Guidelines  

· We invite papers up to 8 pages in length in the style specified at
  http://sites.google.com/site/and2010workshop/submission

· Make submissions online at
  http://www.easychair.org/conferences/?conf=and2010

· Accepted papers will be included in the ACM Digital Library

A selected number of top-quality accepted papers will be invited to
submit expanded versions for publication in the International Journal
of Document Analysis and Recognition (IJDAR) published by Springer for
a special issue.

Important Dates

· Abstract Submission: July 16th, 2010

· Paper Submission: July 20th, 2010

· Notification of Acceptance: August 8th, 2010

· Camera-Ready papers due: August 15th, 2010

Contact

· Shourya Roy - shourya.roy at xerox.com

· L. Venkata Subramaniam - lvsubram at in.ibm.com


-------------------------------------------------------------------------
Message diffuse par la liste Langage Naturel <LN at cines.fr>
Informations, abonnement : http://www.atala.org/article.php3?id_article=48
English version       : 
Archives                 : http://listserv.linguistlist.org/archives/ln.html
                                http://liste.cines.fr/info/ln

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  : http://www.atala.org/
-------------------------------------------------------------------------