gr-nlp-toolkit

This repository contains the models used in the gr-nlp-toolkit project.

The toolkit includes the following models, all designed specifically for processing the Greek language:

• Named Entity Recognition (NER): Identifies and classifies named entities in Greek text, such as names of people, organizations, and locations.
• Dependency Parsing (DP): Analyzes the grammatical structure of Greek sentences by identifying relationships between words and their dependencies.
• Part Of Speech tagging (POS): Tags each word in Greek text with its corresponding part of speech (e.g., noun, verb, adjective), along with its morphological features.

Note: These models cannot be used as standalone tools; they are integrated into the gr-nlp-toolkit and can only be utilized through it.

Paper

The software was presented as a paper at COLING 2025. Read the full technical report/paper here: https://aclanthology.org/2025.coling-demos.17/

If you use our toolkit, please cite it:

@inproceedings{loukas-etal-coling2025-greek-nlp-toolkit,
    title = "{GR}-{NLP}-{TOOLKIT}: An Open-Source {NLP} Toolkit for {M}odern {G}reek",
    author = "Loukas, Lefteris  and
      Smyrnioudis, Nikolaos  and
      Dikonomaki, Chrysa  and
      Barbakos, Spiros  and
      Toumazatos, Anastasios  and
      Koutsikakis, John  and
      Kyriakakis, Manolis  and
      Georgiou, Mary  and
      Vassos, Stavros  and
      Pavlopoulos, John  and
      Androutsopoulos, Ion",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven  and
      Mather, Brodie  and
      Dras, Mark",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: System Demonstrations",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-demos.17/",
    pages = "174--182",
}

References

While many methodology details are shared in the GR-NLP-TOOLKIT paper publication @ COLING 2025 (see above), additional research details can be found here:

1. C. Dikonimaki, "A Transformer-based natural language processing toolkit for Greek -- Part of speech tagging and dependency parsing", BSc thesis, Department of Informatics, Athens University of Economics and Business, 2021. http://nlp.cs.aueb.gr/theses/dikonimaki_bsc_thesis.pdf (POS/DP/Morphological tagging processor)

2. N. Smyrnioudis, "A Transformer-based natural language processing toolkit for Greek -- Named entity recognition and multi-task learning", BSc thesis, Department of Informatics, Athens University of Economics and Business, 2021. http://nlp.cs.aueb.gr/theses/smyrnioudis_bsc_thesis.pdf (NER processor)

3. A. Toumazatos, J. Pavlopoulos, I. Androutsopoulos, & S. Vassos, "Still All Greeklish to Me: Greeklish to Greek Transliteration." In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) (pp. 15309-15319). https://aclanthology.org/2024.lrec-main.1330/ (Greeklish-to-Greek processor)