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.
Augmenty is an augmentation library based on spaCy for augmenting texts.
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
We specifically test the claim that new information decoupling behavior of media can be used to reliably detect change in news media content originating in a negative event, using a Bayesian approach to change point detection.
An easy straightforward tutorial for fine-tuning a Danish BERT using simpletransformers
A curated list of teaching resources for the convenience of myself and others.
How do democracies react and cope as the COVID-19 crisis unfolds and with what effects? This is the core question we ask in the HOPE project - “How Democracies Cope with COVID-19: A Data-Driven Approach”.