@inproceedings{MahlowGruenHolupireketal.2015, author = {Cerstin Mahlow and Christian Gr{\"u}n and Alexander Holupirek and Marc H. Scholl}, title = {A framework for retrieval and annotation in digital humanities using XQuery full text and update in BaseX}, series = {DocEng 2012 : proceedings of the 2012 ACM Symposium on Document Engineering; September 4 - 7, 2012, Paris, France}, publisher = {ACM}, address = {Paris [u.a.]}, doi = {10.1145/2361354.2361398}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:352-213637}, pages = {195 -- 204}, year = {2015}, abstract = {A key difference between traditional humanities research and the emerging field of digital humanities is that the latter aims to complement qualitative methods with quantitative data. In linguistics, this means the use of large corpora of text, which are usually annotated automatically using natural language processing tools. However, these tools do not exist for historical texts, so scholars have to work with unannotated data. We have developed a system for systematic iterative exploration and annotation of historical text corpora, which relies on an XML database (BaseX) and in particular on the Full Text and Update facilities of XQuery.}, language = {en} }