BibTeX

@inProceedings{volodina-etal-2023-dalaj-326817,
	title        = {DaLAJ-GED – a dataset for Grammatical Error Detection tasks on Swedish},
	booktitle    = {Proceedings of the 12th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2023)},
	editor       = {David Alfter and Elena Volodina and Thomas François and Arne Jönsson and Evelina Rennes},
	author       = {Volodina, Elena and Ali Mohammed, Yousuf and Berdicevskis, Aleksandrs and Bouma, Gerlof and Öhman, Joey},
	year         = {2023},
	publisher    = { Linköping Electronic Conference Proceedings},
	address      = {Linköping },
	ISBN         = {978-91-8075-250-3},
	pages        = {94--101},
}

@article{volodina-etal-2024-swedish-340630,
	title        = {Swedish word family resource},
	abstract     = {The article introduces a novel lexical resource for Swedish based on word family principles. The development of the Swedish Word Family (SweWF) resource is set into the context of linguistic complexity in second language acquisition. The SweWF is particularly appropriate for that, given that it contains lexical items used in second language corpora, namely, in a corpus of coursebook texts, and in a corpus of learner essays. The main focus of the article is on the construction of the resource with its user interface and on its applicability for research, although it also opens vast possibilities for practical applications for language learning, testing and assessment. We demonstrate the value of the resource through several case studies.},
	journal      = {ITL-INTERNATIONAL JOURNAL OF APPLIED LINGUISTICS},
	author       = {Volodina, Elena and Ali Mohammed, Yousuf and Tiedemann, Therese Lindstrom},
	year         = {2024},
}

@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},
}

@inProceedings{volodina-etal-2021-dalaj-311725,
	title        = {DaLAJ - a dataset for linguistic acceptability judgments for Swedish},
	abstract     = {We present DaLAJ 1.0, a Dataset for Linguistic Acceptability Judgments for Swedish, comprising 9 596 sentences in its first version. DaLAJ is based on the SweLL second language learner data (Volodina et al., 2019), consisting of essays at different levels of proficiency. To make sure the dataset can be freely available despite the GDPR regulations, we have sentence-scrambled learner essays and removed part of the metadata about learners, keeping for each sentence only information about the mother tongue and the level of the course where the essay has been written. We use the normalized version of learner language as the basis for DaLAJ sentences, and keep only one error per sentence. We repeat the same sentence for each individual correction tag used in the sentence. For DaLAJ 1.0 four error categories of 35 available in SweLL are used, all connected to lexical or word-building choices. The dataset is included in the SwedishGlue benchmark. Below, we describe the format of the dataset, our insights and motivation for the chosen approach to data sharing.},
	booktitle    = {Proceedings of the 10th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2021), Online},
	author       = {Volodina, Elena and Ali Mohammed, Yousuf and Klezl, Julia },
	year         = {2021},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköping},
	ISBN         = {978-91-7929-625-4},
}

@inProceedings{volodina-etal-2021-coderoomor-311724,
	title        = {CoDeRooMor: A new dataset for non-inflectional morphology studies of Swedish},
	abstract     = {The paper introduces a new resource, CoDeRooMor, for studying the morphology of modern Swedish word formation. The approximately 16.000 lexical items in the resource have been manually segmented into word-formation morphemes, and labeled for their categories, such as prefixes, suffixes, roots, etc. Word-formation mechanisms, such as derivation and compounding have been associated with each item on the list. The article describes the selection of items for manual annotation and the principles of annotation, reports on the reliability of the manual annotation, and presents tools, resources and some first statistics. Given the”gold” nature of the resource, it is possible to use it for empirical studies as well as to develop linguistically-aware algorithms for morpheme segmentation and labeling (cf statistical subword approach). The resource is freely available through Språkbanken-Text.},
	booktitle    = { 23rd Nordic Conference on Computational Linguistics (NoDaLiDa) Proceedings, May 31–2 June, 2021, Reykjavik, Iceland Online / Simon Dobnik, Lilja Øvrelid (Editors)},
	author       = {Volodina, Elena and Ali Mohammed, Yousuf and Lindström Tiedemann, Therese},
	year         = {2021},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköping},
	ISBN         = {978-91-7929-614-8},
}

@inProceedings{volodina-etal-2020-towards-300069,
	title        = {Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays},
	abstract     = {This article reports on an ongoing project aiming at automatization of pseudonymization of learner essays. The process includes three steps: identification of personal information in an unstructured text, labeling for a category, and pseudonymization. We experiment with rule-based methods for detection of 15 categories out of the suggested 19 (Megyesi et al., 2018) that we deem important and/or doable with automatic approaches. For the detection and labeling steps, we use resources covering personal names, geographic names, company and university names and others. For the pseudonymization step, we replace the item using another item of the same type from the above-mentioned resources. Evaluation of the detection and labeling steps are made on a set of manually anonymized essays. The results are promising and show that 89% of the personal information can be successfully identified in learner data, and annotated correctly with an inter-annotator agreement of 86% measured as Fleiss kappa and Krippendorff's alpha.},
	booktitle    = {Proceedings of the 28th International Conference on Computational Linguistics (COLING), December 8-13, 2020, Barcelona, Spain (Online)},
	author       = {Volodina, Elena and Ali Mohammed, Yousuf and Derbring, Sandra and Matsson, Arild and Megyesi, Beata},
	year         = {2020},
	publisher    = {International Committee on Computational Linguistics},
	ISBN         = {978-1-952148-27-9},
}