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 Electronic Conference Proceedings 190 /  NEALT Proceedings Series 47},
	address      = {Linköping, Sweden},
	ISBN         = {978-91-7929-460-1},
}