BibTeX

@inProceedings{klezl-etal-2022-exploring-321958,
	title        = {Exploring Linguistic Acceptability in Swedish Learners’ Language },
	abstract     = {We present our initial experiments on binary classification of sentences into linguistically correct versus incorrect ones in Swedish using the DaLAJ dataset (Volodina et al., 2021a). The nature of the task is bordering on linguistic acceptability judgments, on the one hand, and on grammatical error detection task, on the other. The experiments include models trained with different input features and on different variations of the training, validation, and test splits. We also analyze the results focusing on different  error  types and errors  made  on  different proficiency levels. Apart from insights into which features and approaches work well for this task, we present first benchmark results on this dataset. The implementation is based on  a  bidirectional  LSTM  network  and  pre-trained  FastText embeddings, BERT embeddings, own word and character embeddings, as well as part-of-speech tags and dependency labels as input  features. The best model used BERT embeddings and a training and validation set enriched with additional correct sentences. It  reached an  accuracy of 73%  on one  of  three  test sets  used  in  the  evaluation. These promising results illustrate that the dataand format of DaLAJ  make a valuable  new resource  for research  in acceptability  judgements in Swedish.},
	booktitle    = {Proceedings of the 11th Workshop on Natural Language Processing for Computer-Assisted Language Learning (NLP4CALL 2022)},
	author       = {Klezl, Julia and Ali Mohammed, Yousuf and Volodina, Elena},
	year         = {2022},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköping, Sweden},
	ISBN         = {978-91-7929-459-5 },
}

@incollection{alimohammed-etal-2022-annotation-321989,
	title        = {Annotation Management Tool: A Requirement for Corpus Construction},
	abstract     = {We present an annotation management tool, SweLL portal, that has been developed for the purposes of the SweLL infrastructure project for building a learner corpus of Swedish (Volodina et al., 2019). The SweLL portal has been used for supervised access to the database, data versioning, import and export of data and metadata, statistical overview, administration of annotation tasks, monitoring of annotation tasks and reliability controls. The development of the portal was driven by visions of longitudinal sustainable data storage and was partially shaped by situational needs reported by portal users, including project managers, researchers, and annotators.},
	booktitle    = {Selected Papers from the CLARIN Annual Conference 2021, Virtual Event, 2021, 27–29 September / Monica Monachini and Maria Eskevich (eds.)},
	author       = {Ali Mohammed, Yousuf and Matsson, Arild and Volodina, Elena},
	year         = {2022},
	publisher    = {Linköping Electronic Conference },
	address      = {Linköping, Sweden},
	ISBN         = {978-91-7929-444-1},
	pages        = {101--108},
}

@inProceedings{volodina-etal-2022-swedish-321985,
	title        = {Swedish L2 profile - a tool for exploring L2 data.},
	abstract     = {Learner corpus researchers, NLP researchers, as well as Digital Humanities and Social Sciences in general, rely on access to various data sets for empirical analysis, statistical insights, and/or for model building. However, interpretation of data is a non-trivial task and there is a need for data visualization tools. One such attempt is the Swedish L2 profile (SweL2P) – an ongoing project setting up the first digital tool allowing users to explore written Swedish learner language from a linguistic point of view.},
	booktitle    = {Learner Corpus Research conference, 22-24 September, Padua, Italy},
	author       = {Volodina, Elena and Lindström Tiedemann, Therese and Ali Mohammed, Yousuf},
	year         = {2022},
	address      = {Universitá degli Studi di Padova, Padua, Italy},
}

@incollection{volodina-etal-2022-lyxig-321974,
	title        = {Lyxig språklig födelsedagspresent from the Swedish Word Family.},
	abstract     = {Morphology and lexical resources are known to be two of Lars Borin’s biggest research passions.
We have, therefore, prepared a short description of a new kind of a lexical resource for Swedish,
the Swedish Word Family. The resource is compiled based on learner corpora, and contains lexical
items manually analyzed for derivational morphology.},
	booktitle    = {Live and Learn- Festschrift in honor of Lars Borin},
	author       = {Volodina, Elena and Ali Mohammed, Yousuf and Lindström Tiedemann, Therese},
	year         = {2022},
	publisher    = {Department of Swedish, Multilingualism, Language Technology},
	address      = {Gothenburg, Sweden},
	ISBN         = {978-91-87850-83-7},
}