@incollection{HagenJannidisWitt2022, author = {Thora Hagen and Fotis Jannidis and Andreas Witt}, title = {Word sense alignment and disambiguation for historical encyclopedias}, series = {Graphs and Networks in the Humanities 2022. Technologies, Models, Analyses, and Visualizations. 6th International Conference, 3. – 4. February 2022, Online.}, editor = {Tara Andrews and Franziska Diehr and Thomas Efer and Andreas Kuczera and Joris van Zundert}, publisher = {Graphen \& Netzwerke; AG des Verbandes Digital Humanities im deutschsprachigen Raum e.V.}, address = {Gie{\"s}en}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-109834}, year = {2022}, abstract = {This paper will address the challenge of creating a knowledge graph from a corpus of historical encyclopedias with a special focus on word sense alignment (WSA) and disambiguation (WSD). More precisely, we examine WSA and WSD approaches based on article similarity to link messy historical data, utilizing Wikipedia as aground-truth component – as the lack of a critical overlap in content paired with the amount of variation between and within the encyclopedias does not allow for choosing a ”baseline” encyclopedia to align the others to. Additionally, we are comparing the disambiguation performance of conservative methods like the Lesk algorithm to more recent approaches, i.e. using language models to disambiguate senses.}, language = {en} }