@inproceedings{L16-1711,
 abstract = {This paper introduces an open source, interoperable generic software tool set catering for the entire workflow of creation, migration, annotation, query and analysis of multi-layer linguistic corpora. It consists of four components: Salt, a graph-based meta model and API for linguistic data, the common data model for the rest of the tool set; Pepper, a conversion tool and platform for linguistic data that can be used to convert many different linguistic formats into each other; Atomic, an extensible, platform-independent multi-layer desktop annotation software for linguistic corpora; ANNIS, a search and visualization architecture for multi-layer linguistic corpora with many different visualizations and a powerful native query language. The set was designed to solve the following issues in a multi-layer corpus workflow: Lossless data transition between tools through a common data model generic enough to allow for a potentially unlimited number of different types of annotation, conversion capabilities for different linguistic formats to cater for the processing of data from different sources and/or with existing annotations, a high level of extensibility to enhance the sustainability of the whole tool set, analysis capabilities encompassing corpus and annotation query alongside multi-faceted visualizations of all annotation layers.
},
 address = {Portorož, Slovenia},
 author = {Stephan Druskat and Volker Gast and Thomas Krause and Florian Zipser},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {4492--4499},
 publisher = {European Language Resources Association (ELRA)},
 title = {corpus-tools.org: An Interoperable Generic Software Tool Set for Multi-layer Linguistic Corpora},
 url = {https://www.aclweb.org/anthology/L16-1711},
 year = {2016}
}