DaCy

Last updated on Jul 1, 2022
Code Demo Documentation

DaCy is a Danish natural language processing framework made with SpaCy. Its largest pipeline has achieved State-of-the-Art performance on Named entity recognition, part-of-speech tagging and dependency parsing for Danish. This repository contains material for using the DaCy, reproducing the results and guides on usage of the package. Furthermore, it also contains behavioural tests for biases and robustness of Danish NLP pipelines. The package is free available on GitHub and you can always try out a demo for en named entity tagging capabilities here.

NLP Danish NLP Low-resource NLP
Kenneth Enevoldsen
Kenneth Enevoldsen
PhD student in Multimodal Representation Learning

My research interests is in multimodal representation learning with application in decision support systems in Psychiatry and in the Covid-19 response.

Related

Posts

DaCy: New Fast and Efficient State-of-the-Art in Danish NLP!
The short story of how I achieved state-of-the-art on all Danish NLP tasks Using SpaCy v3 and a series of other open-source tools
Last updated on Mar 9, 2021 8 min read
Project Code Download
DaCy: New Fast and Efficient State-of-the-Art in Danish NLP!

Events

DaCy and SpaCy
A presentation of DaCy, an Efficient Danish State-of-the-Art NLP pipeline build on SpaCy, at Extra Bladet, one of the biggest Danish news outlet.
Mar 16, 2021 00:00
Project Slides
DaCy and SpaCy