% pubman genre = article @article{item_3258795, title = {{Cross-Linguistic Data Formats, advancing data sharing and re-use in comparative linguistics}}, author = {Forkel, Robert and List, Johann-Mattis and Greenhill, Simon J. and Rzymski, Christoph and Bank, Sebastian and Cysouw, Michael and Hammarstr{\"o}m, Harald and Haspelmath, Martin and Kaiping, Gereon A. and Gray, Russell D.}, language = {eng}, issn = {2052-4463}, doi = {10.1038/sdata.2018.205}, publisher = {Nature Publishing Group}, address = {London, United Kingdom}, year = {2018}, 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 software package for validation and manipulation, a basic ontology which links to more general frameworks, and usage examples of best practices.}}, journal = {{Scientific Data}}, volume = {5}, eid = {180205}, }