The Humit Tagger is a morphological AI tagger for Norwegian Bokmål and Nynorsk developed at Humit, University of Oslo.
The tagger is based on a neural network, more precisely a pre-trained BERT model for Norwegian, developed by the National Library of Norway. The tagger is a so-called sequence classifier, which selects morphological tags but not lemmas.
In this first version of the Humit Tagger, the full-form word list from Norsk ordbank is used as a basis for lemma selection.
The Humit Tagger is a morphological AI tagger for Norwegian Bokmål and Nynorsk developed at Humit, University of Oslo.
The tagger is based on a neural network, more precisely a pre-trained BERT model for Norwegian, developed by the National Library of Norway. The tagger is a so-called sequence classifier, which selects morphological tags but not lemmas.
In this first version of the Humit Tagger, the full-form word list from Norsk ordbank is used as a basis for lemma selection.
Utvidet metadata
resource Common Info:
resource Type: toolService
identification Info:
resource Name: The Humit Tagger
resource Name: Humit-taggeren
description: The Humit Tagger is a morphological AI tagger for Norwegian Bokmål and Nynorsk developed at Humit, University of Oslo.
The tagger is based on a neural network, more precisely a pre-trained BERT model for Norwegian, developed by the National Library of Norway. The tagger is a so-called sequence classifier, which selects morphological tags but not lemmas.
In this first version of the Humit Tagger, the full-form word list from Norsk ordbank is used as a basis for lemma selection.
validation Mode Details: So far, the tagger has only been evaluated on a test part of the Norwegian Dependency Treebank where there is only one correct answer for each word form. The Humit tagger then has an accuracy of 0.98 for tags and 0.99 for lemmas.
validation Report Unstructured:
document Unstructured: See home page
https://www.hf.uio.no/humit/english/resources/humit-tagger/index.html
resource Documentation Info:
documentation Unstructured:
document Unstructured: See home page
https://www.hf.uio.no/humit/english/resources/humit-tagger/index.html
documentation Unstructured:
document Unstructured: Haug, D. T. T., Yildirim, A., Hagen, K., & Nøklestad, A. (2023). Rules and neural nets for morphological tagging of Norwegian-Results and challenges. NEALT Proceedings Series, 425-435.
operating System: See https://github.com/humit-oslo/humit-tagger
dc:type
toolService
dc:title
Humit-taggeren
dc:identifier
oai:tekstlab.uio.no:humit-tagger
dc:description
The Humit Tagger is a morphological AI tagger for Norwegian Bokmål and Nynorsk developed at Humit, University of Oslo.
The tagger is based on a neural network, more precisely a pre-trained BERT model for Norwegian, developed by the National Library of Norway. The tagger is a so-called sequence classifier, which selects morphological tags but not lemmas.
In this first version of the Humit Tagger, the full-form word list from Norsk ordbank is used as a basis for lemma selection.