At Språkbanken Text, we have a research theme that relates to computational modeling of word (meaning) change called (computational) lexical semantic change. In this theme, we have both research projects and a larger research program.
In the VR-funded project Towards Computational Lexical Semantic Change Detection (2019-2022) we aim to find automatic, corpus-based methods for detecting semantic change and lexical replacement for Swedish and English. Within this project we have released a book on Computational approaches to semantic change, held the 1st International Workshop on Computational Approaches to Historical Language Change and second International Workshop on Computational Approaches to Historical Language Change 2021 (LChange’21). We co-organized the SemEval2020 Task 1 for Unsupervised Lexical Semantic Change Detection and released our manually annotated dataset used for the challenge, and released the largest resource of graded contextualized, diachronic word meaning.
In the RJ-funded program Change is Key!, we will develop computational methods for detecting language change to facilitate the study of contemporary and historical societies. We will study both lexical semantic change, lexical replacements as well as semantic (synchronic) variation, for language technology, historical linguistics, lexicography, analytical sociology, gender studies and literary studies, in a truly cross-disciplinary program. Change is Key! will start in 2022 and span six years, with a total of 11 researchers and one research engineer involved. There are partners from IMS Stuttgart, Queen Mary University of London, University of Lund, Institute for Analytical Sociology (IAS) Linköping University, KU Leuven, and University of Gothenburg.