Noisy unstructured text data is ubiquitous in real-world communications. Text produced by processing signals intended for human use such as printed/handwritten documents, spontaneous speech, and camera-captured scene images, are prime examples. Telephonic conversations between call center agents and customers often see 30-40% word error rates, even using state-ofthe-art ASR. OCR error rates for hardcopy documents can range widely from 2-3% for clean inputs to 50% or higher depending on the quality of the page image, the complexity of the layout, aspects of the typography, etc. Individual variabilities in handwriting make this a particularly difficult form of input and error rates here are often substantially higher than for machine print text. In spite of the tremendous challenges such data presents, it is pervasive in applications of interest to corporations and government organizations.

Recognition errors are not the sole source of noise; natural language and the creative ways that humans use it can create problems for computational techniques. Electronic text from the Internet (emails, message boards, newsgroups, blogs, wikis, chat logs and web pages), contact centers (customer complaints, emails, call transcriptions, message summaries), and mobile phones (text messages) is often noisy, containing spelling errors, abbreviations, non-standard words, false starts, repetitions, missing punctuation, missing case information, and pause-filling words such as “um” and “uh” in the case of spoken conversations.

AND 2009 is a workshop devoted to issues arising from the need to contend with noisy inputs, the impact noise can have on downstream applications, and the demands it places on document analysis. The Third Workshop on Analytics for Noisy Unstructured Text Data will build on two previous successful AND workshops held in 2007 (in conjunction with the 20th International Joint Conference on Artificial Intelligence) and in 2008 (in conjunction with the 31st Annual International ACM SIGIR Conference).

Topics of Interest
o Noise induced by document analysis techniques and its impact on downstream applications
o Formal models for noise, including characterization and classification of noise
o Treatment of noisy data in specific application areas, including historical texts, multilingual documents, blogs, chat / SMS logs, social network analysis, patent search, and machine translation
o Data sets, benchmarks, and evaluation techniques for analysis of noisy text
o All other topics arising from noise and its effects on textual data
Submission Guidelines

Full papers may be submitted following the guidelines specified on the AND 2009 website:
http://and2009workshop.googlepages.com/

Important Dates (tentative)
Paper Submission: April 20, 2009
Notification of Acceptance: May 20, 2009
Camera-Ready papers due: June 20, 2009