The Department for Natural Language Processing (Abteilung Automatische Sprachverarbeitung (ASV) has a proven record in infrastructure building for linguistic resources, text-mining and semantic processing of unstructured data, as well as many areas of language processing including morphological analysis, tagging and topic modeling. The group offers one of the largest linguistic data resources for German comprising about 32 million words types. Similar data, although smaller in size, is available for many other languages. In the past, the department has successfully carried out a number of German Research Society funded projects on natural language processing and the group has a strong record of third party industrial funding, including Volkswagen, Daimler AG, and the Leipzig University Library.
Key responsibilities in READ: Transkribus web interface. Language modelling and toolkit. Since it is impossible to deal with all European languages in the project, ASV will develop a toolkit which will enable users to access large sets of language resources, or to build adequate language resources (lexicons, corpora, etc.) for their own language of interest with a minimum of effort.