Papers by Joanna Dolińska
POS Tagging for the Endangered Dagur Language (2024.lrec-main)
Copied to clipboard
| Challenge: | a recent study has focused on the so-called "dominant" languages, but it has not been inclusive in terms of language equality. |
| Approach: | They propose to use POS tagging to automatically annotate Dagur, an endangered Mongolic language . they use a manually annotated corpus to test transfer of models from other languages . |
| Outcome: | The proposed method can be used to document and revitalize endangered languages . the proposed model can be trained on Buryat, the only Mongolic language included in the corpus . |