Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered
Computation and Language
2021-05-27 v1
Abstract
We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out of which 17 are endangered. The neural models follow the same tagset as the FSTs in order to make it possible to use them as fallback systems together with the FSTs. The source code, models and datasets have been released on Zenodo.
Keywords
Cite
@article{arxiv.2105.12428,
title = {Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered},
author = {Mika Hämäläinen and Niko Partanen and Jack Rueter and Khalid Alnajjar},
journal= {arXiv preprint arXiv:2105.12428},
year = {2021}
}
Comments
The 23rd Nordic Conference on Computational Linguistics (NoDaLiDa 2021)