Author =       {Bering, Christian and Drozdzynski, Witold and Erbach, Gregor and Guasch, Clara and Homola, Petr and Lehmann, Sabine and Hong, Li and Krieger, Hans-Ulrich and Piskorski, Jakub and Sch{\"a}fer, Ulrich and Shimada, Atsuko and Siegel, Melanie and Xu, Feiyu and Ziegler-Eisele, Dorothee},
  Title =        {Corpora and evaluation tools for multilingual named entity grammar development},
  BookTitle =    {Proceedings of Multilingual Corpora Workshop at Corpus Linguistics 2003},
  Year =         {2003},
  Pages =        {42--52},
  Address =      {Lancaster},
  Month =        {3},
  Abstract = 	{We present an effort for the development of multilingual named entity grammars in a unification-based finite-state formalism (SProUT). Following an extended version of the MUC7 standard, we have developed Named Entity Recognition grammars for German, Chinese, Japanese, French, Spanish, English, and Czech. The grammars recognize person names, organizations, geographical locations, currency, time and date expressions. Subgrammars and gazetteers are shared as much as possible for the grammars of the different languages. Multilingual corpora from the business domain are used for grammar development and evaluation. The annotation format (named entity and other linguistic information) is described. We present an evaluation tool which provides detailed statistics and diagnostics, allows for partial matching of annotations, and supports user-defined mappings between different annotation and grammar output formats. },
  URL =  {}