Adapting computational methods to challenges in historical research at scale

University of Helsinki (Finland)

Drawing from CASCADE’s expertise in both the conceptual understanding of different types of semantic change, as well as the methods to computationally model such changes, this project will focus on ensuring that the computational approaches measure what they’re supposed to measure. This includes fine-tuning the methods to capture different types of change, as well as ensuring that the measures derived are robust against external confounders, which may arise either from the data itself or from the uneven performance of the methods themselves. Further, the project involves building adaptable environments for both of these, which should enable the easy application of these methods to new data and questions. The selected doctoral candidate should have prior knowledge in natural language processing/language technology and/or data science.

Further information about the project, the position and how to apply is available here.

Further information can also be obtained by contacting the supervisor, Prof. Mikko Tolonen (