Do LSTMs really work so well for PoS tagging?–A replication study
A recent study by Plank et al.(2016) found that LSTM-based PoS taggers considerably
improve over the current state-of-the-art when evaluated on the corpora of the Universal …
improve over the current state-of-the-art when evaluated on the corpora of the Universal …
Named-entity recognition for Norwegian
B Johansen - Proceedings of the 22nd Nordic Conference on …, 2019 - aclanthology.org
NER is the task of recognizing and demarcating the segments of a document that are part of
a name and which type of name it is. We use 4 different categories of names: Locations …
a name and which type of name it is. We use 4 different categories of names: Locations …
[PDF][PDF] Joint ud parsing of norwegian bokmål and nynorsk
This paper investigates interactions in parser performance for the two official standards for
written Norwegian: Bokmål and Nynorsk. We demonstrate that while applying models across …
written Norwegian: Bokmål and Nynorsk. We demonstrate that while applying models across …
NorGramBank: a 'Deep'treebank for Norwegian
H Dyvik, P Meurer, V Rosén, K De Smedt… - Proceedings of the …, 2016 - aclanthology.org
We present NorGramBank, a treebank for Norwegian with highly detailed LFG analyses. It is
one of many treebanks made available through the INESS treebanking infrastructure …
one of many treebanks made available through the INESS treebanking infrastructure …
NARC–Norwegian anaphora resolution corpus
Abstract We present the Norwegian Anaphora Resolution Corpus (NARC), the first publicly
available corpus annotated with anaphoric relations between noun phrases for Norwegian …
available corpus annotated with anaphoric relations between noun phrases for Norwegian …