Language Technology
for Cultural Heritage Data
(LaTeCH 2007)

The Workshop on Language Technology for Cultural Heritage Data will be held in conjunction with the 45th Annual Meeting of the Association for Computational Linguistics, which will take place June 23-30, 2007, in Prague, Czech Republic.

Scope and Topics

Museums, archives, and libraries around the world maintain large collections of cultural heritage objects, such as archaeological artefacts, sound recordings, historic manuscripts, or preserved animal specimens. Large scale digitisation projects are currently underway to make these collections more accessible. Of equal importance, however, is the development of powerful tools to search, link, enrich, and mine the digitised data. Language technology has an important role to play in this, even for collections which are primarily non-textual, since text is the pervasive medium used for metadata. At the same time, the cultural heritage domain poses special challenges for the NLP community, including the use of historic or non-standard language, the presence of OCR or transcription errors in the data, and the necessity to deal with data from various media.

Papers are invited on, but not limited to, the following topics:

• enriching cultural heritage data by inducing metadata
• dealing with linguistic variation and non-standard or non-contemporary use of language
• automatic error detection and cleaning
• adapting existing NLP tools for the cultural heritage domain
• linking and retrieving information from different sources, media, and languages
• representing cultural heritage data to different audiences (personalisation, text simplification, text summarisation, text generation from databases, hypertext generation)
• knowledge discovery in cultural heritage data

Submissions

Authors are invited to submit full papers on original, unpublished work in the topic area of this workshop. Submissions should be formatted using the ACL 2007 stylefiles, which are available at available at http://ufal.mff.cuni.cz/acl2007/styles/, and should not exceed 8 pages.

The reviewing of the papers will be blind and the papers should not include the authors' names and affiliations. Each submission will be reviewed by at least two members of the program committee. Accepted papers will be published in the workshop proceedings.

Papers should be submitted as PDF no later than March 26, 2007, via the following website: http://www.softconf.com/acl07/ACL07-WS4/submit.html

Important Dates

• March 26 - Deadline for workshop papers
• April 23 - Notification of acceptance
• May 6 - Camera-ready papers due
• June 28 - Workshop held at ACL 2007

Registration

Information on registration and registration fees will be provided at the ACL conference web page: http://ufal.mff.cuni.cz/acl2007/.

Organising Committee

Programme Committee

Contact