BibTeX

@article{volodina-etal-2019-swell-285609,
	title        = {The SweLL Language Learner Corpus: From Design to Annotation},
	abstract     = {The article presents a new language learner corpus for Swedish, SweLL, and the methodology from collection and pesudonymisation to protect personal information of learners to annotation adapted to second language learning. The main aim is to deliver a well-annotated corpus of essays written by second language learners of Swedish and make it available for research through a browsable environment. To that end, a new annotation tool and a new project management tool have been implemented, – both with the main purpose to ensure reliability and quality of the final corpus. In the article we discuss reasoning behind metadata selection, principles of gold corpus compilation and argue for separation of normalization from correction annotation.},
	journal      = {Northern European Journal of Language Technology},
	author       = {Volodina, Elena and Granstedt, Lena and Matsson, Arild and Megyesi, Beáta and Pilán , Ildikó  and Prentice, Julia and Rosén, Dan and Rudebeck, Lisa  and Schenström, Carl-Johan and Sundberg, Gunlög and Wirén, Mats},
	year         = {2019},
	volume       = {6},
	pages        = {67--104},
}

@inProceedings{volodina-etal-2018-annotation-275361,
	title        = {Annotation of learner corpora: first SweLL insights.},
	abstract     = {This is a concise description of experiences with learner corpus annotation performed within SweLL project. Experiences include work with legal issues, anonymization, error annotation, normalization and questions relating to quality of annotation. },
	booktitle    = {Proceedings of SLTC 2018, Stockholm, October 7-9, 2018},
	author       = {Volodina, Elena and Granstedt, Lena and Megyesi, Beáta and Prentice, Julia and Rosén, Dan and Schenström, Carl-Johan and Sundberg, Gunlög  and Wirén, Mats},
	year         = {2018},
}

@inProceedings{megyesi-etal-2018-learner-275359,
	title        = {Learner Corpus Anonymization in the Age of GDPR: Insights from the Creation of a Learner Corpus of Swedish},
	abstract     = {This paper reports on the status of learner corpus anonymization for the ongoing research infrastructure project SweLL. The main project aim is to deliver and make available for research a well-annotated corpus of essays written by second language (L2) learners of Swedish. As the practice shows, annotation of learner texts is a sensitive process demanding a lot of compromises between ethical and legal demands on the one hand, and research and technical demands, on the other. Below, is a concise description of the current status of pseudonymization of language learner data to ensure anonymity of the learners, with numerous examples of the above-mentioned compromises.},
	booktitle    = {Proceedings of the 7th Workshop on NLP for Computer Assisted Language Learning (NLP4CALL 2018) at SLTC, Stockholm, 7th November 2018},
	editor       = {Ildikó Pilán and Elena Volodina and David Alfter and Lars Borin},
	author       = {Megyesi, Beata and Granstedt, Lena and  Johansson, Sofia and Prentice, Julia and Rosén, Dan and Schenström, Carl-Johan and Sundberg, Gunlög and  Wirén , Mats and Volodina, Elena},
	year         = {2018},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköpings universitet},
	ISBN         = {978-91-7685-173-9},
}