Cross-lingual parsing with polyglot training and multi-treebank learning: a Faroese case study
Barry, JamesORCID: 0000-0003-3051-585X, Wagner, JoachimORCID: 0000-0002-8290-3849 and Foster, JenniferORCID: 0000-0002-7789-4853
(2019)
Cross-lingual parsing with polyglot training and multi-treebank learning: a Faroese case study.
In: The 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), 3 - 5 Nov 2019, Hong Kong, China.
ISBN 978-1-950737-78-9
Cross-lingual dependency parsing involves transferring syntactic knowledge from one language to another. It is a crucial component for inducing dependency parsers in low-resource scenarios where no training data for a language exists. Using Faroese as the target language, we compare two approaches using annotation projection: first, projecting from multiple monolingual source models; second, projecting from a single polyglot model which is trained on the combination of all source languages. Furthermore, we reproduce multi-source projection (Tyers et al., 2018), in which dependency trees of multiple sources are combined. Finally, we apply multi-treebank modelling to the projected treebanks, in addition to or alternatively to polyglot modelling on the source side. We find that polyglot training on the source languages produces an overall trend of better results on the target language but the single best result for the target language is obtained by projecting from monolingual source parsing models and then training multi-treebank POS tagging and parsing models on the target side.
Metadata
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Workshop
Refereed:
Yes
Uncontrolled Keywords:
Faroese language resources; knowledge transfer across related languages; dependency parsing for low-resource languages
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019).
.
Association for Computational Linguistics. ISBN 978-1-950737-78-9