[Sigdl-l] CFP: ASIST 2011 Workshop on the IMPACT Center for Digitization

[Martens, Betsy V.]

CFP: ASIST 2011 Workshop on the IMPACT Center for Digitization. Project Results and
Future Path of Practice and Research.
October 12, 2011. New Orleans, Louisiana.
http://cis.uni-muenchen.de/asist2011workshop
***************************************************************************

Recent large scale digitization initiatives had a major focus on full text recognition of
historical texts, primarily in the form of out-of-copyright newspapers and books. However,
the available Optical Character Recognition (OCR) software provides far from satisfactory
results for historical documents. This is due to issues inherent in the material such as warped
pages, bleed-through, historic fonts, broken and irregular characters, complex layouts, and
due to language issues such as historical spelling variants, extinct vocabulary and mixed
language documents e.g. English and Latin, Dutch and French etc.

In this workshop we sketch the results of a large scale project Improving Access to Text
(IMPACT) where a team of scientists, industry partners and library professionals has been
developing new approaches to OCR and language technology to address challenges in
historical materials from five centuries in now nine European languages since its start in 2008.
We will discuss the future direction of work in the area of text digitization from the point of
view of the IMPACT Centre of Competence in Text Digitization that will be launched in
October 2011. This Centre will make digitization of historical printed text in Europe better,
faster, cheaper by sharing expertise and providing access to tools for all parts of the
digitization workflow, as well as tools, services and facilities for further advancement of the
State of the Art in this field.  One of the main aims of the workshop presented at 2011 ASIS&tT is
to outline the opportunities for the research community in historical document processing to
engage with this Centre of Competence. We hope to create a sustainable collaboration
between the efforts of the major European Libraries as well as private and public research
institutions within IMPACT during the last four years and the digitization community in
North America.

The workshop will be held in a more informal way than a conference with permanent
opportunity to start discussions, also during a presentation. All participants
will have an opportunity to briefly present their current research on
digitization. Besides paper presentations we will have a guided discussion to elaborate the
future direction of the research of the European IMPACT Centre of Competence for Text
Digitization as well as its collaboration with digitization researchers in North America.

*Paper Format*
Potential attendees are encouraged to submit brief papers between two and four pages. Papers
can be a summary of current research results, of best practices or a position paper.
The paper should be two to four pages long in ACM format
<http://www.acm.org/sigs/publications/proceedings-templates>.
Please email .pdf or .doc versions to Christoph Ringlstetter (christoph at cis.uni-muenchen.de)
by *12 pm September 4, 2011*.

While papers are not due until September 4, we ask that you
inform us about your intention to participate as early as you can
(before August 22) to help us with the organization and planning.
By notifying us early, we will try to confirm your space at the
workshop in time for you to take advantage of the ASIS&T early
registration deadline (Aug 26).

*Workshop Themes*
* Imaging and Image Acquisition
* Digital Archiving Considerations
* Historical Collections
* Digital Document Restoration/Improving Readability
* Optical Character Recognition (OCR)
* Information Extraction, Retrieval and Presentation
* Methods for Detecting and Correcting Errors in Digitized Text
* Classification, Grouping and Hyperlinking of Digitized Documents
* Historical Language Change and its Effects on Digitization, Search and
Presentation
* Surveys Relating to Best Practices

*Discussion Points and Questions*
* How to select what to digitize.
* Technical issues of imaging and OCR.
* Full Text. Which qualities can we expect.
* Information Extraction and Search.
* Presentation of a digitized Collection.
* Future Trends in Digitization.

*Important Dates*
August 22, 2011: Intention to participate sent to the organizers
August 26, 2011: ASIS&T early registration deadline
September 4, 2011: Papers due
September 12, 2011: Notifications
October 12, 2011: Workshop

*Organizers*
Hildelies Balk, Project Manager of IMPACT, Head of the European Projects for Research and
Development in the National Library of the Neverlands (KB).
Clemens Neudecker, Technical Project Manager, IMPACT.
Aley Conteh, Digitization Program Manager at the British Library (BL).
Katrien Depuydt, Head of the Language Database Department at the Institute for Lexicology
of the Netherlands (INL)
Christoph Ringlstetter, University of Munich, Center for Information and Language
Processing


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.asis.org/pipermail/sigdl-l/attachments/20110813/911734ed/attachment.html