AND 2008

SIGIR-08 Workshop

2nd Workshop on Analytics for Noisy Unstructured Text Data 24 July 2008, Singapore

http://and2008workshop.googlepages.com/

Call for Papers

Workshop Description and Objectives Noise is an unavoidable fact of life. It can manifest itself at the earliest stages of processing in the form of degraded inputs that our systems must be prepared to handle. People are adept when it comes to pattern recognition tasks involving typeset or handwritten documents or recorded speech, machines less-so. From the perspective of down-stream processes that take as their inputs the outputs of recognition systems, including document analysis and OCR, noise can be viewed as the errors made by earlier stages of processing, which are rarely perfect and sometimes quite brittle. Noisy unstructured text data is also found in informal settings such as online chat, SMS, email, message board and newsgroup postings, blogs, wikis and web pages. In addition to the aforementioned recognition errors, such text may contain spelling errors, abbreviations, non-standard terminology, missing punctuation, misleading case information, as well as false starts, repetitions, and pause-filling sounds such as "um" and "uh" in the case of speech. By its very nature, noisy text warrants moving beyond traditional text analytics techniques. Noise introduces challenges that need special handling, either through new methods or improved versions of existing ones. We invite you to submit your own unique perspectives on this important topic.

Topics of Interest (not limited to) Information Retrieval and Information Extraction on noisy texts IR-related tasks (classification, clustering, genre recognition, document summarization, keyword search) on noisy texts Formal models for noise, characterization and classification of noise Treatment of noisy data in special application fields - Historical Texts - Multilingual Texts - Blogs - Chat logs/SMS - Social Network Analysis - Patent Search - Optical Character Recognition - Automated Speech Recognition - Machine Translation Data sets, benchmarks and evaluation techniques for analysis of noisy texts

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.

Important Dates Paper Submission: May 16th, 2008 Notification of Acceptance: Jun 6th, 2008 Camera-Ready papers due: Jun 20th, 2008 Workshop at SIGIR 2008: Jul 24th, 2008 Submission Requirements We invite papers up to 8 pages in length in the style specified at http://and2008workshop.googlepages.com/submission There will also be a Best Student Paper Award. Papers with a student as the primary author/presenter will be eligible for this award.

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 Daniel Lopresti Lehigh University Shourya Roy IBM Research, India Research Lab Klaus U Schulz University of Munich L. Venkata Subramaniam IBM Research, India Research Lab

Workshop contacts This CfP was obtained from WikiCFP
 * L. V. Subramaniam lvsubram@in.ibm.com
 * Shourya Roy rshourya@in.ibm.com