ATEM-2004: The AAAI-04 Workshop on
Adaptive Text Extraction and Mining

July 26, 2004
San Jose, California




Workshop Description

The amount of information that is available in the form of unstructured and semistructured documents keeps increasing at an unprecedented rate. Even though these terabytes of text contain invaluable information for virtually every domain of activity, the existing tools for accessing and exploiting this data fall short of users' needs, thus preventing the effective use of these rich information sources.
Recent years have brought significant interest and progress in developing techniques for the automatic extraction and mining of text corpora. Adaptive text extraction and mining (ATEM) is an extremely active area of research that lies at the intersection of diverse fields such as information extraction, text mining, machine learning, data mining, link analysis, information retrieval, natural language processing, and information integration. As developments in any of these fields have an immediate effect on the other ones, it is crucial to ensure the free exchange of ideas among researchers that work on various aspects of ATEM. The purpose of this workshop is to bring together researchers and practitioners from all these communities, so that they can discuss recent results and open problems.


The workshop's topics include, but are not limited to, applying machine learning and data mining to: Of particular interest are "provoking" papers raising questions such as "is parsing necessary for high-quality information extraction?", "are ontologies really useful for ATEM?", or "is domain-independent ATEM really doable?".

Workshop format

The workshop will consist of two full-paper sessions, a short-paper session, an invited presentation, and a panel discussion on lessons learned and future trends in the field.

Attendance & Submission

The planned workshop attendance is about 30 people. The attendees must submit either a long/short paper (6 and 3 pages, respectively), or a 1-page research statement. The submisions, which must comply with the AAAI-2004 style, will be emailed to the workshop chair as PS/PDF attachements ( the emails must use the subject "ATEM-04 submission").

Important dates:

Organizing Committee:

Additional reviewers: