micm-nlp¶
A research framework for NLP — the whole pipeline in a single YAML, run alone or in groups. Builds on the HuggingFace stack and adds a layer of features of its own.
pip install micm-nlp
micm-nlp is developed at the Muskhelishvili Institute of Computational Mathematics (MICM), Georgian Technical University.
It has backed two peer-reviewed publications:
Cross-Prompt Encoder for Low-Performing Languages
Findings of IJCNLP–AACL 2025; ACL Anthology
Beso Mikaberidze, Temo Saghinadze, Simon Ostermann, Philipp MüllerA Comparison of Different Tokenization Methods for the Georgian Language
ICNLSP 2024; ACL Anthology
Beso Mikaberidze, Teimuraz Saghinadze, Guram Mikaberidze, Raphael Kalandadze, Konstantine Pkhakadze, Josef van Genabith, Simon Ostermann, Lonneke van der Plas, Philipp Müller
What micm-nlp offers¶
Contribution |
In short |
Answers |
|---|---|---|
unit config → unit run |
How do I describe a whole run in one place, and make it reproducible? |
|
group config → many unit runs |
How do I run many variations, and collect their results together? |
|
ready-made functionality |
What can I do here that the HuggingFace stack does not already do? |
Links¶
PyPI |
|
Source |
|
Issue tracker |
|
Releases |
|
Changelog |
|
XPE paper |
|
Tokenization paper |
|
MICM |
|
Contact |
beso.mikaberidze@gmail.com |
Acknowledgements¶
micm-nlp was developed at the Muskhelishvili Institute of Computational Mathematics (MICM, Georgian Technical University), in close research collaboration with Teimuraz Saghinadze (MICM), Simon Ostermann (DFKI / CERTAIN), and Philipp Müller (Max Planck Institute for Intelligent Systems), whose joint work on the Cross-Prompt Encoder (XPE) drove much of the framework’s design and validation.
This work was partially supported by the European Union under Horizon Europe project “GAIN” (GA #101078950) and by the German Federal Ministry of Research, Technology and Space (BMFTR) as part of the project TRAILS (01IW24005).
Citation¶
If you use micm-nlp in your research, please cite the package and (if relevant to your work) the XPE paper that drove its design:
@software{micm_nlp,
author = {Mikaberidze, Beso},
title = {micm-nlp: a research framework for {NLP} built on {HuggingFace}},
organization = {Muskhelishvili Institute of Computational Mathematics, Georgian Technical University},
url = {https://github.com/bmikaberidze/micm-nlp},
version = {0.4.0},
year = {2026},
}
@inproceedings{mikaberidze-etal-2025-cross,
title = {Cross-Prompt Encoder for Low-Performing Languages},
author = {Mikaberidze, Beso and Saghinadze, Temo and Ostermann, Simon and M{\"u}ller, Philipp},
booktitle = {Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
month = dec,
year = {2025},
address = {Mumbai, India},
publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},
url = {https://aclanthology.org/2025.findings-ijcnlp.144/},
doi = {10.18653/v1/2025.findings-ijcnlp.144},
pages = {2380--2393},
}