@article{Forkel2018a, abstract = {The amount of available digital data for the languages of the world is constantly increasing. Unfortunately, most of the digital data are provided in a large variety of formats and therefore not amenable for comparison and re-use. The Cross-Linguistic Data Formats initiative proposes new standards for two basic types of data in historical and typological language comparison (word lists, structural datasets) and a framework to incorporate more data types (e.g. parallel texts, and dictionaries). The new specification for cross-linguistic data formats comes along with a Book package for validation and manipulation, a basic ontology which links to more general frameworks, and usage examples of best practices.}, author = {Forkel, Robert and List, Johann-Mattis and Greenhill, Simon J. and Rzymski, Christoph and Bank, Sebastian and Cysouw, Michael and Hammarström, Harald and Haspelmath, Martin and Kaiping, Gereon A. and Gray, Russell D.}, doi = {https://doi.org/10.1038/sdata.2018.205}, journal = {Scientific Data}, keywords = {cross-linguistic data formats, standardization, _calc, reproducibility}, number = {180205}, pages = {1-10}, title = {Cross-Linguistic Data Formats, advancing data sharing and re-use in comparative linguistics}, url = {https://www.nature.com/articles/sdata2018205}, volume = {5}, year = {2018} }