Metadata-Version: 2.1
Name: daluke
Version: 0.0.1.post2
Summary: A Danish-speaking language model with entity-aware self-attention
Home-page: https://github.com/peleiden/daLUKE
Author: Søren Winkel Holm, Asger Laurits Schultz
Author-email: s18911@dtu.dk, s183912@dtu.dk
License: MIT License
Download-URL: https://pypi.org/project/daluke/
Keywords: nlp,ai,pytorch,ner
Platform: UNKNOWN
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: matplotlib
Requires-Dist: seqeval
Requires-Dist: torch (>=1.8.0)
Requires-Dist: transformers (>=4.3.3)
Requires-Dist: pelutils[ds] (==0.6.7)
Requires-Dist: click (>=7.0.0)
Requires-Dist: tqdm
Requires-Dist: wget
Provides-Extra: full
Requires-Dist: danlp ; extra == 'full'
Requires-Dist: pyicu ; extra == 'full'
Requires-Dist: wikipedia2vec ; extra == 'full'
Requires-Dist: umap-learn ; extra == 'full'
Requires-Dist: scikit-learn ; extra == 'full'
Requires-Dist: scipy ; extra == 'full'

# daLUKE
![](daluke-mascot.png)
[![pytest](https://github.com/peleiden/daLUKE/actions/workflows/pytest.yml/badge.svg?branch=master)](https://github.com/peleiden/daLUKE/actions/workflows/pytest.yml)

Implementation of [LUKE](https://github.com/studio-ousia/luke) on Danish text corpus with a focus on named entity recognition. 





