# DaCy: A Unified Framework for Danish NLP

arXiv: https://arxiv.org/abs/2107.05295 · HTML: https://mlsanity.com/paper/2107.05295/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Muppet: Massive Multi-task Representations with Pre-Finetuning](https://mlsanity.com/paper/2101.11038/) (2021)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [ConvBERT: Improving BERT with Span-based Dynamic Convolution](https://mlsanity.com/paper/2008.02496/) (2020)
- [Polyglot: Distributed Word Representations for Multilingual NLP](https://mlsanity.com/paper/1307.1662/) (2013)
- [The Danish Gigaword Project](https://mlsanity.com/paper/2005.03521/) (2020)

## Built on by (most cited first, 10 of 10)

- [ScandEval: A Benchmark for Scandinavian Natural Language Processing](https://mlsanity.com/paper/2304.00906/) (2023)
- [Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines](https://mlsanity.com/paper/2308.12635/) (2023)
- [calamanCy: A Tagalog Natural Language Processing Toolkit](https://mlsanity.com/paper/2311.07171/) (2023)
- [Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language](https://mlsanity.com/paper/2409.20147/) (2024)
- [Augmenty: A Python Library for Structured Text Augmentation](https://mlsanity.com/paper/2312.05520/) (2023)
- [DANSK and DaCy 2.6.0: Domain Generalization of Danish Named Entity Recognition](https://mlsanity.com/paper/2402.18209/) (2024)
- [SnakModel: Lessons Learned from Training an Open Danish Large Language Model](https://mlsanity.com/paper/2412.12956/) (2024)
- [SDUs DAISY: A Benchmark for Danish Culture](https://mlsanity.com/paper/2601.19930/) (2026)
- [Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament](https://mlsanity.com/paper/2609.26346/) (2026)
- [Retrieving Biblical Intertextual References in Karen Blixen's Seven Gothic Tales](https://mlsanity.com/paper/2609.35765/) (2026)

## Abstract (arXiv)

Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish. We present DaCy: a unified framework for Danish NLP built on SpaCy. DaCy uses efficient multitask models which obtain state-of-the-art performance on named entity recognition, part-of-speech tagging, and dependency parsing. DaCy contains tools for easy integration of existing models such as for polarity, emotion, or subjectivity detection. In addition, we conduct a series of tests for biases and robustness of Danish NLP pipelines through augmentation of the test set of DaNE. DaCy large compares favorably and is especially robust to long input lengths and spelling variations and errors. All models except DaCy large display significant biases related to ethnicity while only Polyglot shows a significant gender bias. We argue that for languages with limited benchmark sets, data augmentation can be particularly useful for obtaining more realistic and fine-grained performance estimates. We provide a series of augmenters as a first step towards a more thorough evaluation of language models for low and medium resource languages and encourage further development.