@incollection{HagenKetzanJannidisetal.2020, author = {Thora Hagen and Erik Ketzan and Fotis Jannidis and Andreas Witt}, title = {Twenty-two historical encyclopedias encoded in TEI: a new resource for the Digital Humanities}, series = {Proceedings of the The 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. December 12, 2020, Barcelona, Spain (Online)}, editor = {Stefania DeGaetano and Anna Kazantseva and Nils Reiter and Stan Szpakowicz}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA}, isbn = {978-1-952148-34-7}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-102512}, pages = {112 -- 120}, year = {2020}, abstract = {This paper accompanies the corpus publication of EncycNet, a novel XML/TEI annotated corpus of 22 historical German encyclopedias from the early 18th to early 20th century. We describe the creation and annotation of the corpus, including the rationale for its development, suggested methodology for TEI annotation, possible use cases and future work. While many well-developed annotation standards for lexical resources exist, none can adequately model the encyclopedias at hand, and we therefore suggest how the TEI Lex-0 standard may be modified with additional guidelines for the annotation of historical encyclopedias. As the digitization and annotation of historical encyclopedias are settling on TEI as the de facto standard, our methodology may inform similar projects.}, language = {en} }