Full documentation here: https://npedrazzini.github.io/OldSlavNet/.
Pre-modern Slavic neural-network (Bi-LSTM) dependency parser.
If you use our pretrained model to parse new pre-modern Slavic texts, please cite [1]. The parser supersedes the previous version described in [2], which can be downloaded from the old releases.
[1] Pedrazzini, Nilo & Hanne M. Eckhoff. 2021. OldSlavNet: A scalable Early Slavic dependency parser trained on modern language data. Software Impacts 100063.
@article{oldslavnet,
title={OldSlavNet: A scalable Early Slavic dependency parser trained on modern language data},
author={Pedrazzini, Nilo and Eckhoff, Hanne M.},
journal={Software Impacts},
pages={100063},
year={2021},
}
[2] Pedrazzini, Nilo. 2020. Exploiting Cross-Dialectal Gold Syntax for Low-Resource Historical Languages: Towards a Generic Parser for Pre-Modern Slavic. In Folgert Karsdorp, Barbara McGillivray, Adina Nerghes & Melvin Wevers (eds.), Proceedings of the Workshop on Computational Humanities Research, November 18–20, 2020, Amsterdam, The Netherlands (CEUR Workshop Proceedings, Vol. 2723), 237-247. http://ceur-ws.org/Vol-2723/short48.pdf.
@inproceedings{pedrazzini2020,
title={Exploiting Cross-Dialectal Gold Syntax for Low-Resource Historical Languages: Towards a Generic Parser for Pre-Modern Slavic},
author={Pedrazzini, Nilo},
journal={CEUR Workshop Proceedings},
volume={2723},
pages={237--247},
year={2020},
url={http://ceur-ws.org/Vol-2723/short48.pdf},
}