New approaches for extracting heterogeneous reference data
- Beginn: 15.05.2023 13:00
- Ende: 16.05.2023 18:15
- Ort: mpilhlt & online
Programme
Monday 15 May 2023
13:00-13:30 Opening
13:30-14:50 Presentations 1
Aleksandra Kaye/Bernardo S. Buarque/Malte Vogl/Raphael Schlattmann (ModelSEN project, MPI for History of Science): Socio-epistemic networks of Polish migrants in Latin America – a challenge for heterogeneous reference extraction
Raphael Schlattmann/Malte Vogl/Aleksandra Kaye/Bernardo S. Buarque (ModelSEN project, MPI for History of Science): Automated construction of historical semiotic networks – Can person-names within textual contexts be mapped to structured references?
Discussion
14:50-15:00 Coffee Break
15:00-16:20 Presentations 2
Johannes Riedl (University Library Tübingen): A Description of the Work in Progress of the Transformation of the Handbuch der Keilschriftenliteratur
Victor Westrich (Academy of Sciences and Literature, Mainz): Extraction of primary and secondary sources from the Regesta Imperii
16:20-16:30 Coffee Break
16:30-18:15 Presentations 4
Kilian Lüders/Bent Stohlmann (HU Berlin): Extraction of string-citations in court data
Thiago Freitas Hansen/Rafael Castro Andrade (Universidade Federal do Paraná/Positivo University, Curitiba): Words and Social Rights in Brazil (1933-1941)
Will Hanley/J. Hernandez/M. Nagales/B. Goff (Florida State University): Citation Analysis of International Law Journals, 1869-1939
Discussion
18:15-18:45 Break
18:45-19:30 Discussion of Whitepaper idea
Tuesday 16 May 2023
10:00-11:20 Presentations 4
Diego de la Hera/Dominic Dall’Osto (Wikimedistas Calamuchita/Univ. of Zurich): Using Cita to support reference extraction workflows from Zotero
Julia Hütten/Jeff Huang (mpilhlt/Brown University): Automatically characterizing the heterogeneous interpretations of a citation for incorporating into a hosted dataset
Discussion
11:20-11:40 Coffee Break
11:40-13:00 Presentations 5
Christian Boulanger (mpilhlt): Order from Chaos: Potential and Limits of CRF-based Reference Extraction from Footnotes
Andreas Wagner (mpilhlt): Obtaining Training Data - Different Tasks, Different Options
Discussion
13:00-14:30 Lunch Break
14:30-15:50 Presentations 6
Olga Pagnotta/Silvio Peroni (University of Bologna): Measuring the Performances of AnyStyle and Grobid against a Gold Strandard
Anastasiia Iurshina/Tobias Backes/Ahsan Shahid/Philipp Mayer (Univ. of Stuttgart): Outcite: end-to-end reference processing pipeline
Discussion
15:50-16:15 Coffee Break
16:15-18:00 How to go forward?
18:00-18:15 Closing