A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- OA-A systematic comparison of methods for low-resource dependency parsing
Final published version, 525 KB, PDF document
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
Publisher | Association for Computational Linguistics |
Publication date | 2019 |
Pages | 1105-1116 |
DOIs | |
Publication status | Published - 2019 |
Event | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) - Hong Kong, China Duration: 1 Nov 2019 → 1 Nov 2019 |
Conference
Conference | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
---|---|
Location | Hong Kong, China |
Periode | 01/11/2019 → 01/11/2019 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 240407654