# DaCy

> DaCy is a Danish text processing pipeline built using SpaCy

**Wikidata**: [Q126084888](https://www.wikidata.org/wiki/Q126084888)  
**Source**: https://4ort.xyz/entity/dacy

## Summary
DaCy is a Danish text processing pipeline built using SpaCy, designed for natural language processing tasks in Danish. It provides tools for part-of-speech tagging, named-entity recognition, parsing, and analysis of Danish text. The software is open-source and available under the Apache Software License 2.0.

## Key Facts
- DaCy is a Danish text processing pipeline built using SpaCy
- The software is open-source and licensed under Apache Software License 2.0
- Latest stable version is 2.4.1, released on 2023-03-14
- First stable version 1.0.0 was released on 2021-07-10
- Used for enriching, part-of-speech tagging, parsing, analysis, and named-entity recognition
- Source code is hosted on GitHub at https://github.com/centre-for-humanities-computing/DaCy
- Official website is https://centre-for-humanities-computing.github.io/DaCy/
- Listed in the Social Sciences and Humanities Open Marketplace
- Described at https://marketplace.sshopencloud.eu/tool-or-service/qeaxdg

### Q: What is DaCy used for?
A: DaCy is used for natural language processing tasks in Danish, including part-of-speech tagging, named-entity recognition, parsing, and text analysis. It helps enrich Danish text data for various applications.

### Q: What programming framework does DaCy use?
A: DaCy is built using SpaCy, a popular open-source library for advanced natural language processing in Python.

### Q: Is DaCy free to use?
A: Yes, DaCy is open-source software available under the Apache Software License 2.0, making it free to use, modify, and distribute.

### Q: Where can I find the source code for DaCy?
A: The source code for DaCy is hosted on GitHub at https://github.com/centre-for-humanities-computing/DaCy.

### Q: What is the latest version of DaCy?
A: The latest stable version of DaCy is 2.4.1, released on 2023-03-14.

## Why It Matters
DaCy addresses a critical gap in natural language processing tools for the Danish language, which has historically been underserved compared to major languages like English. By providing a robust, open-source pipeline built on the well-established SpaCy framework, DaCy enables researchers, developers, and organizations to process Danish text efficiently for various applications including academic research, business intelligence, and digital humanities projects. The software's availability under an open license democratizes access to advanced NLP capabilities for Danish, supporting linguistic research, cultural preservation, and technological development in Danish-speaking communities. Its integration with SpaCy also means it benefits from ongoing improvements in the broader NLP ecosystem while maintaining language-specific optimizations.

## Notable For
- First comprehensive Danish NLP pipeline built on the modern SpaCy framework
- Open-source availability under Apache 2.0 license enables broad adoption
- Regular maintenance with frequent version updates since 2021
- Integration with the Social Sciences and Humanities Open Marketplace
- Support for multiple Danish NLP tasks including NER, POS tagging, and parsing

## Body
### Technical Foundation
DaCy is built on SpaCy, a leading open-source library for industrial-strength natural language processing. This foundation provides DaCy with access to modern NLP architectures and efficient processing capabilities while being specifically trained and optimized for the Danish language.

### Version History
The project has seen consistent development since its initial release. Version 1.0.0 launched on 2021-07-10 as the first stable release. The software has progressed through multiple versions including 2.0.0 (2022-08-08), 2.2.7 through 2.2.9 (all released on 2023-01-03), 2.3.0 (2023-01-05), 2.3.1 (2023-01-09), 2.3.2 (2023-02-14), 2.4.0 (2023-03-09), and the current stable version 2.4.1 (2023-03-14).

### Core Capabilities
DaCy supports several fundamental NLP tasks for Danish text:
- Part-of-speech tagging to identify grammatical categories of words
- Named-entity recognition to identify and classify named entities
- Parsing to analyze grammatical structure
- General text analysis and enrichment

### Development and Community
The project is maintained by the Centre for Humanities Computing, with source code available on GitHub. The software's inclusion in the Social Sciences and Humanities Open Marketplace indicates recognition within academic and research communities. The Apache 2.0 license encourages both academic and commercial use while allowing for community contributions and modifications.

## References

1. [Source](https://marketplace.sshopencloud.eu/tool-or-service/qeaxdg)
2. [Source](https://api.github.com/repos/centre-for-humanities-computing/DaCy)
3. [Release 1.0.0. 2021](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v1.0.0)
4. [Release 2.0.0. 2022](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.0.0)
5. [Release 2.2.7. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.2.7)
6. [Release 2.2.8. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.2.8)
7. [Release 2.2.9. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.2.9)
8. [Release 2.3.0. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.3.0)
9. [Release 2.3.1. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.3.1)
10. [Release 2.3.2. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.3.2)
11. [Release 2.4.0. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.4.0)
12. [Release 2.4.1. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.4.1)
13. [Release 2.4.2. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.4.2)
14. [Release 2.5.0. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.5.0)
15. [Release 2.5.1. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.5.1)
16. [Release 2.5.2. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.5.2)
17. [Release 2.6.0. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.6.0)
18. [Release 2.7.0. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.0)
19. [Release 2.7.1. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.1)
20. [Release 2.7.2. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.2)
21. [Release 2.7.3. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.3)
22. [Release 2.7.4. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.4)
23. [Release 2.7.5. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.5)
24. [Release 2.7.6. 2023](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.6)
25. [Release 2.7.7. 2024](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.7)
26. [Release 2.7.8. 2024](https://github.com/centre-for-humanities-computing/DaCy/releases/tag/v2.7.8)