Within the last decade language models like GPT3 or BERT have become the standard in Natural Language Processing (NLP) across a wide variety of tasks from translation to hate speech detection. Even low-resource languages like Danish have their own language model, but Norwegian models perform better than Danish model!? This talk will walk you through the current state and shortcoming of the Danish NLP and how we plan to improve them through a nationwide cross-sector collaboration.
DaCy is a State-of-the-Art Danish natural language processing framework made with 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.
DaCy and Spacy by Kenneth Enevoldsen | 2021-05-16
Agenda What is SpaCy and why should you care?
Speed and multitasking Integration Costomicability Loading and using DaCy
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