Computational Linguistics & Phonetics Co
mputational Linguistics & Phonetics Fachrichtung 4.7Universit344t des Saarlan
des

Text Mining for Historical Documents: Schedule



Introductory Meeting / Vorbesprechung 12.1.2009


Seminar Schedule (preliminary)

Week One
Monday 16.02.
9:30-11:00
11:00-11:15 Coffee Break
11:15-12:45
  • From potsherds to pop songs: types of primary sources. (Torsten Kopp)
  • How and where to find primary sources? (Daniel Quinten)
12:45-14:00 Lunch Break
14:00-15:30
  • The digitization of primary sources: possibilities, problems, outlook. (Martin)
  • formation of the groups for the projects and start of the group work
Tuesday 17.02
9:30-11:00
  • Introduction to Computational Linguistics (Caroline)   Slides (.pdf)
  • Detection and Correction of OCR or transcription errors (Hüseyin Mergan)   Slides [.pdf .ppt]
11:00-11:15 Coffee Break
11:15-12:45
  • Dealing with Non-Standard Orthography. (Sabine Hunsicker)   Slides (.pdf)
  • Named Entities: Background (Alexander Volokh)   Slides (.pdf)
12:45-14:00 Lunch Break
14:00-17:00
  • Group Work
Wednesday 18.02
9:30-11:00
  • Named Entity Disambiguation and Linking (Tassilo Barth)   Slides (.pdf)
  • Case Study: The MITCH Project (Caroline)
11:00-11:15 Coffee Break
11:15-12:45
12:45-14:00 Lunch Break
14:00-17:00
  • Group Work
Thursday 19.02
9:30-11:00
11:00-11:15 Coffee Break
11:15-12:45
  • "How it really was": truth, archives, and the love of old things. (Martin)
12:45-14:00 Lunch Break
14:00-17:00
  • Group Work
Friday 20.02
9:30-11:00
11:00-11:15 Coffee Break
11:15-12:45
  • Group Work
12:45-14:00 Lunch Break
14:00-17:00
  • Taking Stock: What has been done in the first week?
Week Two
Monday 23.02.
Rosenmontag
Tuesday 24.02.
9:30-17:00 Group Work
Wednesday 25.02.
9:30-17:00 Group Work
Thursday 24.02.
9:30-17:00 Group Work
Friday 24.02.
10:15-13:15 Presentation of the Group Projects
  • Extracting information about murders from the Broadsides (Alexander, Hüseyin, Katrin, Torsten)   Slides (.pdf)

  • SCOPE: Subjects connecting people, Kabinettsprotokolle der Bundesregierung (Antonia, Daniel, Fabian, Ghamdan, Tassilo)