urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50:0 SND doi-10-23695-4a7m-mk50 0 urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.ResourcePackage:2.0 urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.OtherMaterialScheme:2.0 urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.OrganizationScheme-0:2.0 urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.Organization-0:2.0 Språkbanken Text urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.StudyUnit:2.0 doi-10-23695-4a7m-mk50 Ordklasstaggningsmodell: Flair POS-tagging model: Flair urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.Individual-0:2.0 Individual Göteborgs universitet University of Gothenburg Göteborgs universitet University of Gothenburg 2024-01-01 10.23695/4A7M-MK50 DOI Models Flair is a powerful NLP library. We provide two Flair models for Swedish part-of-speech tagging. flair_eval is trained on SUC3 with Talbanken_SBX_dev as dev set. The advantage of this model is that it can be evaluated, using Talbanken_SBX_test or SIC2. The evaluation results are reported in the table below. Test set Exact match POS MSD Talbanken_SBX_test 0.978 0.987 0.990 SIC2 0.926 0.940 0.964 Read more about the evaluation here. flair_full is trained on SUC3 + Talbanken_SBX_test + SIC2 with Talbanken_SBX_dev as dev set. We cannot evaluate the performance of this model, but we expect it to perform better than flair_eval, or at least not worse. Using the models on your own Download the model and follow the instructions from Flair. By default, Flair's own embeddings will be used (our experiments show that they provide the best results), but you may use other embeddings instead (or combine them). GPU is strongly recommended. Models Flair is a powerful NLP library. We provide two Flair models for Swedish part-of-speech tagging. flair_eval is trained on SUC3 with Talbanken_SBX_dev as dev set. The advantage of this model is that it can be evaluated, using Talbanken_SBX_test or SIC2. The evaluation results are reported in the table below. Test set Exact match POS MSD Talbanken_SBX_test 0.978 0.987 0.990 SIC2 0.926 0.940 0.964 Read more about the evaluation here. flair_full is trained on SUC3 + Talbanken_SBX_test + SIC2 with Talbanken_SBX_dev as dev set. We cannot evaluate the performance of this model, but we expect it to perform better than flair_eval, or at least not worse. Using the models on your own Download the model and follow the instructions from Flair. By default, Flair's own embeddings will be used (our experiments show that they provide the best results), but you may use other embeddings instead (or combine them). GPU is strongly recommended. urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.TopicalCoverage:2.0 Natural Language Processing Språkbehandling och datorlingvistik urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.Archive:2.0 urn:ddi:se.researchdata:doi-10-23695-4a7m-mk50.Archive-ArchiveSpecificType-AccessType:2.0 0