Computational Linguistics | Further processing of the generated data
For the further processing of the data in order to enable analysis of text via tools of computational linguistics the necessity of intense communication between the computational linguist and the analyst is pivotal. For the anntation and analysis of citation patterns, cross-references, verbal overlaps etc., we decided to use
WebAnno for annotation and ANNIS for analyzing our corpus. WebAnno and Annis will be used in the first analysis phase, to test our annotation model, check rudimentary for citation patterns and overlapping topics. After our analysis, we will evaluate our approach and revise it, if necessary. In the next step, we will add another layer of complexity and start with morphological annotation for more accurate analysis capabilities.
The sustainability of the generated and processed data is guaranteed by the joint eHumanities 2020+-program at our Department of Humanities and the Regional Computing Center of the State of Hamburg.