On Language Spaces, Scales and Cross-Lingual Transfer of UD Parsers

Tanja Samardžić, Ximena Gutierrez-Vasques, Rob van der Goot, Max Müller-Eberstein, Olga Pelloni, Barbara Plank


Abstract
Cross-lingual transfer of parsing models has been shown to work well for several closely-related languages, but predicting the success in other cases remains hard. Our study is a comprehensive analysis of the impact of linguistic distance on the transfer of UD parsers. As an alternative to syntactic typological distances extracted from URIEL, we propose three text-based feature spaces and show that they can be more precise predictors, especially on a more local scale, when only shorter distances are taken into account. Our analyses also reveal that the good coverage in typological databases is not among the factors that explain good transfer.
Anthology ID:
2022.conll-1.18
Volume:
Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Antske Fokkens, Vivek Srikumar
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
266–281
Language:
URL:
https://aclanthology.org/2022.conll-1.18
DOI:
10.18653/v1/2022.conll-1.18
Bibkey:
Cite (ACL):
Tanja Samardžić, Ximena Gutierrez-Vasques, Rob van der Goot, Max Müller-Eberstein, Olga Pelloni, and Barbara Plank. 2022. On Language Spaces, Scales and Cross-Lingual Transfer of UD Parsers. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 266–281, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
On Language Spaces, Scales and Cross-Lingual Transfer of UD Parsers (Samardžić et al., CoNLL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.conll-1.18.pdf
Video:
 https://aclanthology.org/2022.conll-1.18.mp4