@article{ChiarcosRitzStede2012,
  author    = {Chiarcos, Christian and Ritz, Julia and Stede, Manfred},
  title     = {By all these lovely tokens... Merging conflicting tokenizations},
  series = {Language resources and evaluation},
  volume    = {46},
  journal   = {Language resources and evaluation},
  number    = {1},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1574-020X},
  doi       = {10.1007/s10579-011-9161-0},
  pages     = {53 -- 74},
  year      = {2012},
  abstract  = {Given the contemporary trend to modular NLP architectures and multiple annotation frameworks, the existence of concurrent tokenizations of the same text represents a pervasive problem in everyday's NLP practice and poses a non-trivial theoretical problem to the integration of linguistic annotations and their interpretability in general. This paper describes a solution for integrating different tokenizations using a standoff XML format, and discusses the consequences from a corpus-linguistic perspective.},
  language  = {en}
}
@article{StedeHuang2012,
  author    = {Stede, Manfred and Huang, Chu-Ren},
  title     = {Inter-operability and reusability the science of annotation},
  series = {Language resources and evaluation},
  volume    = {46},
  journal   = {Language resources and evaluation},
  number    = {1},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1574-020X},
  doi       = {10.1007/s10579-011-9164-x},
  pages     = {91 -- 94},
  year      = {2012},
  abstract  = {Annotating linguistic data has become a major field of interest, both for supplying the necessary data for machine learning approaches to NLP applications, and as a research issue in its own right. This comprises issues of technical formats, tools, and methodologies of annotation. We provide a brief overview of these notions and then introduce the papers assembled in this special issue.},
  language  = {en}
}