Unlocking the Secrets of the Past: Text Mining for Historical Documents (WS 2009/10)

Schedule

• Vorbesprechung / Introductory Meeting slides (.pdf)

Week One
Monday 22.02.
9:30-10:30	Organisational Stuff, Introduction to NLP (Caroline, slides (.pdf))
10:30-10:45	Coffee Break
10:45-12:15	Introduction to Historic Research: What is History?, Historical Sources, Archives (Martin; Maria, slides (.ppt))
12:15-13:30	Lunch Break
13:30-14:50	OCR Errors Detection and Correction of OCR Errors (1) (Souhail, slides (.pdf)) Detection and Correction of OCR Errors (2) (Michal,slides (.pdf)) )
14:50-15:00	Coffee Break
15:00-17:00	Non-Standard Language Dealing with Non-Standard Orthography (1) (Todd, slides (.odt))) Dealing with Non-Standard Orthography (2) (Johannes, slides (.pdf)) Adapting NLP Tools (Yevgeni, slides (.pdf))
17:00-18:00	Group Formation, Group Work Group 1 HistoRadar Who: Gonzales, Johannes, Uwe, Souhail Data: British Cabinet Protocols What: Changes in opinion of politicians, hotspots, visualisation Code Group 2 Who: Michal, Yevgeni, Todd, Carsten Data: Castro Speech Database What: Visualisation of Document Similarity, Recommender System for most similar speeches Group 3 Who: Sebastian, Sven, Andreas, Christopher Data: Bundeskabinettsprotokolle What: identifying geographical and topical hotspots, participation of politicians wrt topics, visualisation, Group 4 Who: Weijia, Daniel, Jingwen, Chenhua Data: Collection of Images What: IE (field filling) from fulltext descriptions, supervised ML, inferring missing values
Tuesday 23.02
9:30-10:50	Preservation of Digital Data Preservation Issues (Sebastian, slides (.pdf)) Semantic Web Background (Jingwen, slides (.pdf))
10:50-11:05	Coffee Break
11:05-12:25	Semantic Web Ontologies (Weijia, slides (.pdf))) Meta-Data Inferring Meta-Data (Daniel, slides (.pdf))
12:25-13:40	Lunch Break
13:40-15:00	Information Extraction Basics Named Entity Recognition (Uwe, slides (.pdf)) Named Entity Linking and Disambiguation (Andreas, slides (.pdf))
15:00-18:00	Group Work
Wednesday 24.02
9:30-11:30	Text Mining Converting Fieldbooks to Databases (Carsten, slides (.pdf)) Event Recognition (1) (Gonzales, slides (.pdf)) Event Recognition (2) (Chenhua, slides (.pdf))
11:30-12:45	Lunch Break
12:45-14:05	Multi-Modal Data Images and Video (Christopher, slides (.pdf)) Personalisation Personalisation (Sven, slides (.pdf, .pptx))
14:05-18:00	Group Work
Thursday 25.02
9:30-18:00	Group Work
Friday 26.02
9:30-12:00	Taking Stock: Intermediate Group Presentations slides Group 3(.pdf) slides Group 4(.pdf)
12:00-18:00	Group Work
Week Two
Monday 01.03.
9:30-18:00	Group Work
Tuesday 02.03.
9:30-18:00	Group Work
Wednesday 03.03.
9:30-18:00	Group Work
Thursday 04.03.
9:30-18:00	Group Work
Friday 05.03.
9:30-12:30	Presentation of Group Projects Presentation, Group 1 "HistoRadar" (.pdf) Presentation, Group 2 "Castro" (.odp) Presentation, Group 3 (.pdf) Organisational Stuff Information about the report (.pdf)