@inproceedings{crasborn:16023:sign-lang:lrec,
  author    = {Crasborn, Onno and Bank, Richard and Zwitserlood, Inge and van der Kooij, Els and Sch{\"u}ller, Anique and Ormel, Ellen and Nauta, Ellen Yassine and van Zuilen, Merel and van Winsum, Frouke and Ros, Johan},
  title     = {Linking Lexical and Corpus Data for Sign Languages: {NGT} {Signbank} and the {Corpus} {NGT}},
  pages     = {41--46},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna},
  booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining},
  maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Portoro{\v z}, Slovenia},
  day       = {28},
  month     = may,
  year      = {2016},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16023.html},
  abstract  = {How can lexical resources for sign languages be integrated with corpus annotations? We answer this question by discussing an increasingly frequent scenario for sign language resources, where the lexical data are stored in an online lexical database that may also serve as a sign language dictionary, while the annotation data are offline files in the ELAN Annotation Format (EAF). There is by now broad consensus on the need for ID-glosses in corpus annotation, which in turn requires having at least a list of ID-glosses with a description of the phonological form and meaning of the signs. There is less of a consensus on standards for glossing, on practices of sign lemmatisation, and on the types of information that need to be stored in the lexical database. This paper contributes to the establishment of standards for sign language resources by discussing how two data resources for Sign Language of the Netherlands (NGT) are currently being integrated, using the ELAN annotation software for corpus annotation and an adaptation of the Auslan Signbank software as a lexical database. We discuss some of the present relations between two large NGT data sets, and outline some future developments that are foreseen.}
}

@inproceedings{ormel:10036:sign-lang:lrec,
  author    = {Ormel, Ellen and Crasborn, Onno and van der Kooij, Els and van Dijken, Lianne and Nauta, Ellen Yassine and Forster, Jens and Stein, Daniel},
  title     = {Glossing a multi-purpose sign language corpus},
  pages     = {186--191},
  editor    = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam},
  booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies},
  maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Valletta, Malta},
  day       = {22--23},
  month     = may,
  year      = {2010},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10036.html},
  abstract  = {This paper describes the strategies that have been developed for creating consistent gloss annotations in the latest update to the Corpus NGT. Although the project aims to embrace the plea for ID-glosses in Johnston (2008), there is no reference lexicon that could be used in the creation of the annotations. An idiosyncratic strategy was developed that involved the creation of a temporary `glossing lexicon', which includes conventions for distinguishing regional and other variants, true and apparent homonymy, and other difficulties that are specifically related to the glossing of two-handed simultaneous constructions on different tiers.}
}

@inproceedings{crasborn:04005:sign-lang:lrec,
  author    = {Crasborn, Onno and van der Kooij, Els and Broeder, Daan and Brugman, Hennie},
  title     = {Sharing sign language corpora online: proposals for transcription and metadata categories},
  pages     = {20--23},
  editor    = {Streiter, Oliver and Vettori, Chiara},
  booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication},
  maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Lisbon, Portugal},
  day       = {30},
  month     = may,
  year      = {2004},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04005.html},
  abstract  = {This paper presents the results of a European project called ECHO, which included an effort to publish sign language corpora online. The aim of the ECHO project was to explore the intricacies of sharing data using the internet in all areas of the humanities. For sign language, this involved adding a specific profile to the IMDI metadata set for characterizing spoken language corpora, and developing a set of transcription conventions that are useful for a broad audience of linguists. In addition to presenting these results, we outline some options for future technological developments, and bring forward some ethical problems relating to publishing video data on internet.}
}