Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing

Hiroaki Ozaki, Gaku Morio, Terufumi Morishita, Toshinori Miyoshi


Abstract
This paper describes the first report on cross-lingual transfer for semantic dependency parsing. We present the insight that there are twodifferent kinds of cross-linguality, namely sur-face level and mantic level, and try to cap-ture both kinds of cross-linguality by combin-ing annotation projection and model transferof pre-trained language models. Our exper-iments showed that the performance of our graph-based semantic dependency parser almost achieved the approximated upper bound.
Anthology ID:
2021.eacl-main.221
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2586–2594
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.eacl-main.221/
DOI:
10.18653/v1/2021.eacl-main.221
Bibkey:
Cite (ACL):
Hiroaki Ozaki, Gaku Morio, Terufumi Morishita, and Toshinori Miyoshi. 2021. Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2586–2594, Online. Association for Computational Linguistics.
Cite (Informal):
Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing (Ozaki et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.eacl-main.221.pdf
Data
Universal Dependencies