CFP: IJCAI 2007 Workshop on Analytics for Noisy Unstructured Text Data

IJCAI-07 Workshop

Workshop on Analytics for Noisy Unstructured Text Data
8 January 2007 , Hyderabad, India

http://research.ihost.com/and2007

Call for Papers

Workshop Description and Objectives:-

Noisy unstructured text data is found in informal settings such as
online chat, SMS, emails, message boards, newsgroups, blogs, wikis and
web pages. Also, text produced by processing spontaneous speech,
printed text, handwritten text contains processing noise. Text produced
under such circumstances is typically highly noisy containing spelling
errors, abbreviations, non-standard words, false starts, repetitions,
missing punctuations, missing case information, pause filling words
such as "um" and "uh." Such text can be seen in large amounts
in contact centers, on-line chat rooms, OCRed text documents, SMS
corpus etc. The theme of the IJCAI 2007 Conference is "AI and its
benefits to society." In keeping with this theme, this workshop
proposes to look at text analytics of highly noisy text that is
produced in such everyday applications in society.
The goal of the workshop is to focus on the problems encountered in
analyzing such noisy documents coming from various sources. The nature
of the text warrants moving beyond traditional text analytics
techniques. We hope that the workshop will allow researchers to present
current research and development in addressing this challenge. We also
believe that as a result of this workshop there will be sharing of real
life noisy data sets and will result in their becoming available to a
wider research community.

Topics:-

We welcome original research papers that identify key problems related
to noisy text analytics and offer solutions. We particularly encourage
contributions that look at solving real life problems in the different
settings where such data is produced in huge amounts. Potential topics
include (but not limited to):
- NLP techniques for handling noisy unstructured data
- Characterization of the types of noise in documents
- Genre recognition based on the type of noise
- Robust parsing
- Characterizing, modeling and accounting for historical language
change
- Methods for detecting and correcting spelling and grammatical errors
in noisy text
- Information Extraction and Retrieval from noisy text
- Automatic classification and clustering of imprecise documents
- Noise-invariant document summarization techniques
- Issues in keyword search in presence of noise in unstructured data
- Machine Translation for noisy text
- Text analysis techniques for analysis and mining of call-logs,
transcribed calls, web logs, chat logs, email exchanges
- Business Intelligence(BI) applications for contact centers that deal
with noisy data
- Surveys on aspects of text analytics for noisy unstructured data

Participation :-

We hope that the workshop will allow researchers working in areas
related to unstructured data analytics, Natural Language Processing,
Information Extraction, Information Retrieval, etc., to focus on the
needs of users extracting useful information from noisy text. The
target audience is a mixture of academia and industry researchers
working with noisy text. We believe this work is of direct relevance to
domains such as call centers, the world-wide web, and government
organizations that need to analyze huge amounts of noisy data.

IAPR Endorsement:-

This workshop is endorsed by the International Association for Pattern
Recognition (http://www.iapr.org)

Important Dates :-

Paper Submission: September 25th, 2006
Notification of Acceptance: October 23rd, 2006
Camera-Ready papers due: November 8th, 2006
Workshop at IJCAI 2007: January 8th, 2007

Submission Requirements:-

We invite papers up to 8 pages in length in the style specified by
IJCAI at
(pdf: http://www.ijcai-07.org/ijcai07_format.pdf, word:
http://www.ijcai-07.org/ijcai07_format.dot, LaTeX:
http://www.ijcai-07.org/ijcai07_format_latex.tar). Papers should
describe original completed work, work in progress, or interesting
problems or use cases. Submitted papers will be fully refereed based
on the originality and significance of the ideas presented as well as
on technical aspects. Submissions should be made electronically to
lvsubram@xxxxxxxxxx and rshourya@xxxxxxxxxx before September 25th,
2006.

IAPR Best Student Paper Award:-

IAPR is sponsoring the Best Student Paper Prize at AND 2007. One paper
in which a student is the primary author (first author/presenter) will
be selected for the IAPR Best Student Paper Award. The awardee will be
nominated through the paper reviewing process and the final decision
will be made during the workshop. The award carries a cash prize of
$160 which will be given at the conclusion of the workshop.

Publication:-

We are currently in negotiation with a leading publisher for the
proceedings to be available onsite. We have also received tentative
approval for a special issue of a journal for post-workshop publication
of selected papers.

Workshop Chairs:-

Craig Knoblock
University of Southern California
Daniel Lopresti
Lehigh University
Shourya Roy
IBM Research, India Research Lab
L. Venkata Subramaniam
IBM Research, India Research Lab

Workshop contacts:-

- L. V. Subramaniam lvsubram@xxxxxxxxxx
- Shourya Roy rshourya@xxxxxxxxxx


Please visit the workshop website
***** http://research.ihost.com/and2007 *****
for information about participation and submitting papers.

For general information, please visit the IJCAI website
***** http://www.ijcai-07.org *****
*************************************************

.

Relevant Pages