2-year Postdoc position in Change is Key!
We seek a postdoc for a 2-year position at the University of Gothenburg for semantic change detection across multiple time points.
The postdoc is situated in two research projects with closely related themes for computational modeling of lexical semantic change.
The largest part of the position (75%) is within the program “Change is Key!”, a research program funded by Riksbankens Jubileumsfond (RJ), where SBX is the coordinating partner. Here, you will conduct research in automatic detection and analysis of LSC from diachronic texts specifically targeted towards change over multiple (in the order of hundred) time periods. The Change is Key! Program offers a vivid research environment for this exciting and growing cutting-edge research field in NLP. There is a unique opportunity to contribute to the field of LSC, but also to humanities and social sciences through our active collaboration with international researchers in historical linguistics, analytical sociology, gender studies, conceptual history, and literary studies.
The remainder of the position (25%) is conducted within the research project Towards computational lexical semantic change detection (a project funded by a grant from the Swedish Research Council), where SBX is the coordinating partner. The successful applicant will conduct research in this project targeted towards automatic detection and analysis of LSC from diachronic texts.
This postdoc will offer the possibility to strengthen and enhance scientific skills by conducting research with focus on computational modeling of semantic change together with the research groups at SBX, as well as international researchers from KULeuven, IMS Stuttgart, and Queen Mary University of London. If it fits the research plan, there is a possibility of a 3-6 month research stay at one of our partner institutions.
The successful applicant will conduct research in NLP/data science in order to develop and implement methods for modeling lexical semantic change using diachronic texts, with a particular focus on multiple-time point change detection. In particular, you will be using machine learning, and deep learning, to automatically model semantic change using large collections of (historical) texts across hundreds of time points. There is a need for graph theoretical perspectives, alternatively, perspectives from modeling of complex (social) networks. You will evaluate your results on English and Swedish document collections, on evaluation sets like SemEval-tasks for word sense induction, unsupervised semantic change detection, and other existing change testsets. You will also help identify relevant, new testsets.
If time permits, you will use the developed models to investigate qualitative hypotheses posted by researchers from history, linguistics, and social sciences. The research tasks will be defined together with the project/program leader to correspond to the project/program goals, and conducted in an active research environment where in-depth knowledge of methods and evaluation for lexical semantic change exist.