@inproceedings{chenpichler:16028:sign-lang:lrec,
  author    = {Chen Pichler, Deborah and Hochgesang, Julie A. and Simons, Doreen and Lillo-Martin, Diane},
  title     = {Community Input on Re-consenting for Data Sharing},
  pages     = {29--34},
  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/16028.html},
  abstract  = {Development of large sign language corpora is on the rise, and online sharing of such corpora promises unprecedented access to high quality sign language data, with significant time-saving benefits for sign language acquisition research. Yet data sharing also brings complex logistical challenges for which few standardized practices exist, particularly with regard to the protection of participant rights. Although some ethical guidelines have been established for large-scale archiving of spoken or transcribed language data, not all of these are feasible for sign language video data, especially given the relatively small and historically vulnerable communities from which sign language data are typically collected. Our primary focus is the process of re-consenting participants whose original informed consent did not address the possibility of sharing their video data. We describe efforts to develop ethically sound, community-supported practices for data sharing and archiving, summarizing feedback collected from two focus groups including a cross-section of community stakeholders. Finally, we discuss general themes that emerged from the focus groups, placing them in the wider context of similar discussions previously published by other researchers grappling with these same issues, with the goal of contributing to best-practices guidelines for data archiving and sharing in the sign language research community.}
}

@inproceedings{lillomartin:08035:sign-lang:lrec,
  author    = {Lillo-Martin, Diane and Chen Pichler, Deborah},
  title     = {Development of Sign Language Acquisition Corpora},
  pages     = {129--133},
  editor    = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge},
  booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora},
  maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Marrakech, Morocco},
  day       = {1},
  month     = jun,
  year      = {2008},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08035.html},
  abstract  = {Longitudinal, spontaneous production data have long been a cornerstone of language acquisition studies, but building corpora of sign language acquisition data poses considerable challenges. Our experience began with the development of a sign language acquisition corpus more than 15 years ago and has recently included a small-scale experiment in corpus sharing between our two research groups. Our combined database includes regular samples of deaf and hearing children between the ages of 1;06 to 3;06 years acquiring ASL as their native language. The process through which we generate and share transcripts has undergone dramatic changes, always with the triple goal of creating transcripts with sufficient information for the reader to locate regions of interest, while keeping the video fully accessible and minimizing the time required to generate transcripts. In this paper we summarize the various incarnations of our transcription system, from simple Word documents with minimal integration of video, to a combination of FileMaker Pro software integrated with Autolog, to a fully integrated transcript+video package in ELAN. Along the way, we discuss the potential of ELAN to surmount several obstacles that have traditionally stood in the way of large-scale corpus sharing in the sign language acquisition community.}
}