UDapter: Language Adaptation for Truly Universal Dependency Parsing

Ahmet Üstün, Arianna Bisazza, Gosse Bouma, Gertjan van Noord


Abstract
Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a novel multilingual task adaptation approach based on contextual parameter generation and adapter modules. This approach enables to learn adapters via language embeddings while sharing model parameters across languages. It also allows for an easy but effective integration of existing linguistic typology features into the parsing network. The resulting parser, UDapter, outperforms strong monolingual and multilingual baselines on the majority of both high-resource and low-resource (zero-shot) languages, showing the success of the proposed adaptation approach. Our in-depth analyses show that soft parameter sharing via typological features is key to this success.
Anthology ID:
2020.emnlp-main.180
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2302–2315
Language:
URL:
https://aclanthology.org/2020.emnlp-main.180
DOI:
10.18653/v1/2020.emnlp-main.180
Bibkey:
Cite (ACL):
Ahmet Üstün, Arianna Bisazza, Gosse Bouma, and Gertjan van Noord. 2020. UDapter: Language Adaptation for Truly Universal Dependency Parsing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2302–2315, Online. Association for Computational Linguistics.
Cite (Informal):
UDapter: Language Adaptation for Truly Universal Dependency Parsing (Üstün et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/2020.emnlp-main.180.pdf
Video:
 https://slideslive.com/38938768
Code
 ahmetustun/udapter