A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- OA-A systematic comparison of methods for low-resource dependency parsing
Forlagets udgivne version, 525 KB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2019 |
Sider | 1105-1116 |
DOI | |
Status | Udgivet - 2019 |
Begivenhed | 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 Varighed: 1 nov. 2019 → 1 nov. 2019 |
Konference
Konference | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
---|---|
Lokation | Hong Kong, China |
Periode | 01/11/2019 → 01/11/2019 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 240407654