← Search

Data · dataset · 2024

Lemmatization model: Stanza

Listed in Researchdata.se

Models We provide a model that enables lemmatization of Swedish text following the SUC3 standard.

Description

Note that SUC3 lemmatization does not exactly match the SALDO standard that is used in our Korp resources. SUC3 was randomly split into training, validation and test sets (80:10:10).

The model was trained for 30 epochs using the default Stanza settings. The accuracy on the test set is 99.18.

Links

Where it is published

Catalogue records · 1

Topics

Inferred from text
Text 75%
Provenance · 1 source records, 9 field assertions
SourceKeyLast seenRaw
Researchdata.seoai:researchdata.se:doi-10-23695-681b-be74/013 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · researchdata seconnector:researchdata_se@1.0.0
concepts[field].local:field:computer-science-aimapping · researchdata seconnector:researchdata_se@1.0.0
concepts[field].local:field:earth-environmentalmapping · researchdata seconnector:researchdata_se@1.0.0
concepts[field].local:field:humanitiesmapping · researchdata seconnector:researchdata_se@1.0.0
concepts[modality].local:modality:textenrichment · researchdata sekeyword-concept-rules@1.0.0title+description (75%)
descriptionsource · researchdata seconnector:researchdata_se@1.0.0/metadata/dc/description
licensesource · researchdata seconnector:researchdata_se@1.0.0/metadata/dc/rights
publication_datesource · researchdata seconnector:researchdata_se@1.0.0
titlesource · researchdata seconnector:researchdata_se@1.0.0/metadata/dc/title