Empirical Linguistics and Computational Language Modeling – Leibniz ScienceCampus Mannheim/Heidelberg
New technologies today allow us to store and electronically evaluate great volumes of spoken and written language. This is also revolutionising the research conducted in the fields of linguistics, the humanities and cultural studies. New processes, methods and research questions are being created. In order to manage, process, analyse and render usable these great data volumes, it is necessary to develop new tools. This is the challenge taken on by the Leibniz ScienceCampus “Empirical Linguistics and Computational Language Modeling”.
Its key research areas include the preparation and statistical analysis of extensive language resources. The scientists from the fields of linguistics, computer linguistics and computer sciences working here develop language processing models for the German language. These models are intended to make it possible to automatically analyse and interpret language of different genres and domains.
Furthermore, the Leibniz ScienceCampus aims to make these methods and tools usable for investigating research topics in the digital humanities. Fields of application include the stylistic analysis of literary texts and the computer-aided observation of social discourses over extended periods, the results of which can be used to generate or support hypotheses concerning the establishing of new linguistic phenomena or text types.