2003 Workshop on Adaptive Text Extraction and Mining
Monday 22 September 2003  Cavtat-Dubrovnik (Croatia).

held in conjunction with:
14th European Conference on Machine Learning (ECML) 
and the 7th European Conference on Principles and Practice of  Knowledge Discovery in Databases (PKDD)

Workshop Description · Areas of Intererst  · Accepted Papers ·Program · Target Audience · Submission Details · Important Dates  · Organizing Committee 

**** new ! List of accepted Papers ****

Workshop Description
Vast quantities of valuable knowledge are embedded in unstructured textual formats. Petabytes of text are currently available on the public Web, in intranets and other private repositories, and on our personal desktop machines. In many cases, the only way to access such documents is through blunt instruments such as keyword-based document retrieval. In recent years, there has been significant research (and  considerable commercial interest) in technologies for automatically
extracting and mining useful structured knowledge from unstructured text. Current trends suggest a movement away from pure natural language processing approaches requiring the manual development of  rules, to a shallower, less knowledge intensive techniques based on techniques from machine learning, information retrieval and data mining.

Adaptive text extraction and mining is an enabling technology with a wide variety of applications. On the Web, automated knowledge capture from text would open the way for both better retrieval, and advanced business applications (e.g. B2B/B2C applications mediated by knowledge-aware agents). For knowledge management, capturing the knowledge contained in a company’s repositories would encourage knowledge to be shares and reused among employees, improving
efficiency and competitiveness. Extracting information from texts is an important step in capturing knowledge, e.g. for populating databases or ontologies, supporting document annotation (e.g. for the Semantic Web), for learning ontologies, etc.

The workshop will bring together researchers and practitioners from different communities (e.g. machine learning, text mining, natural language processing, information extraction, information retrieval, ontology learning) to discuss recent results and trends in mining texts for knowledge capture. Members of other communities (e.g.  information integration and data mining) could find the workshop very interesting as well. Previous workshops on the use of machine learning for information extraction were held at AAAI-1998, ECAI-2000, and IJCAI-2001.

Areas of Interest
Areas of interest for the workshop include (but  are not limited to):

Target Audience
This workshop is aimed at researchers in the adaptive information extraction community.  Members of other communities also find the workshop  very interesting as well: text mining, information retrieval, information integration, and ontology learning.

ATEM-2003 will accept two types of submissions: long papers that describe completed research (maximum 8 pages); and short papers that describe ongoing work or challenging ideas (maximum 4 pages). Proceedings of the workshop will be published. The most interesting papers presented at the workshop will  be also considered for a special issue of a scientific journal.

Manuscripts must be submitted in either PDF or Postscript and formatted using the style required for the main conference.

Send submissions to
with the subject "ATEM Submission".

Important dates:
papers due Friday 20 June 2003 ****EXTENDED!!!****
acceptance notification Tuesday 15 July 2003 ***CHANGED***
camera-ready copy due Tuesday 22  July 2003 ***CHANGED***
workshop Monday 22 September 2003 [tentative]

Organizing  Committee:
Fabio Ciravegna ·(Primary contact)  p: Computer Science Department, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK · t: +44-114-22-21800 · f: +44-114-22-21810 · e: f.ciravegna at dcs . shef . ac . uk · w: www.dcs.shef.ac.uk/~fabio.
Nicholas Kushmerick  · p: Smart Media Institute, Computer Science Department, University College Dublin, Dublin 4, Ireland · t: +353-1-706-2479 · f: +353-1-269-7262 · e: nick at ucd . ie · w: www.cs.ucd.ie/staff/nick.

Program Committee:

* Valter Crescenzi (Universita` Roma Tre)
* Dayne Freitag (Fair, Isaac and Company)
* Ion Muslea (University of Southern California, Irvine)
* Hwee Tou Ng (National University of Singapore)
* Mark Stevenson (University of Sheffield)
* Roman Yangarber (New York University)