A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages
Parsers are available for only a handful of the world’s languages, since they require lots of training data. How far can we get with just a small amount of training data? We systematically compare a set of simple strategies for improving low-resource parsers: data augmentation, which has not been te...
| Published in: | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
|---|---|
| Main Authors: | , , , |
| Format: | Article in Journal/Newspaper |
| Language: | English |
| Published: |
Association for Computational Linguistics
2019
|
| Subjects: | |
| Online Access: | https://curis.ku.dk/portal/da/publications/a-systematic-comparison-of-methods-for-lowresource-dependency-parsing-on-genuinely-lowresource-languages(e5a689f6-9f8e-4c6a-862e-07c0b179b485).html https://doi.org/10.18653/v1/D19-1102 https://curis.ku.dk/ws/files/240407657/OA_A_systematic_comparison_of_methods_for_low_resource_dependency_parsing.pdf |
| Summary: | Parsers are available for only a handful of the world’s languages, since they require lots of training data. How far can we get with just a small amount of training data? We systematically compare a set of simple strategies for improving low-resource parsers: data augmentation, which has not been tested before; cross-lingual training; and transliteration. Experimenting on three typologically diverse low-resource languages—North Sámi, Galician, and Kazah—We find that (1) when only the low-resource treebank is available, data augmentation is very helpful; (2) when a related high-resource treebank is available, cross-lingual training is helpful and complements data augmentation; and (3) when the high-resource treebank uses a different writing system, transliteration into a shared orthographic spaces is also very helpful. |
|---|