@article{SchmidtBennoehr2008, author = {Thomas Schmidt and Jasmine Benn{\"o}hr}, title = {Rescuing Legacy Data}, series = {Language Documentation and Conservation}, volume = {2}, number = {1}, publisher = {University of Hawaii Press}, address = {Honolulu}, issn = {1934-5275}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-23160}, pages = {109 -- 120}, year = {2008}, abstract = {This paper discusses issues that arise in the transformation of electronic language data from outdated to modern, sustainable formats. We first describe the problem and then present four different cases in which corpora of spoken language were converted from legacy formats to an XML-based representation. For each of the four cases, we describe the conversion workflow and discuss the difficulties that we had to overcome. Based on this experience, we formulate some more general observations about transforming legacy data and conclude with a set of best practice recommendations for a more sustainable handling of language corpora.}, language = {en} }