README.md

metadata

language:
  - sk
tags:
  - pos
license: cc
datasets:
  - universal_dependencies
metrics:
  - accuracy
widget:
  - text: Kde tá ľudská duša drieme?

POS tagger based on SlovakBERT

This is a POS tagger based on SlovakBERT. The model uses Universal POS tagset (UPOS). The model was fine-tuned using Slovak part of Universal Dependencies dataset [Zeman 2017] containing 10k manually annotated Slovak sentences.

Results

The model was evaluated in our paper [Pikuliak et al 2021, Section 4.2]. It achieves $97.84\mathrm{\%}97.84\backslash \%$ accuracy.

Cite

@article{DBLP:journals/corr/abs-2109-15254,
  author    = {Mat{\'{u}}s Pikuliak and
               Stefan Grivalsky and
               Martin Konopka and
               Miroslav Blst{\'{a}}k and
               Martin Tamajka and
               Viktor Bachrat{\'{y}} and
               Mari{\'{a}}n Simko and
               Pavol Bal{\'{a}}zik and
               Michal Trnka and
               Filip Uhl{\'{a}}rik},
  title     = {SlovakBERT: Slovak Masked Language Model},
  journal   = {CoRR},
  volume    = {abs/2109.15254},
  year      = {2021},
  url       = {https://arxiv.org/abs/2109.15254},
  eprinttype = {arXiv},
  eprint    = {2109.15254},
}