Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies

Maryam Aminian, Mohammad Sadegh Rasooli, Mona Diab


Abstract
We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available. We leverage a multitask learning framework coupled with annotation projection. We use syntactic parsing as the auxiliary task in our multitask setup. Our annotation projection experiments from English to Czech show that our multitask setup yields 3.1% (4.2%) improvement in labeled F1-score on in-domain (out-of-domain) test set compared to a single-task baseline.
Anthology ID:
2020.emnlp-main.663
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8268–8274
Language:
URL:
https://aclanthology.org/2020.emnlp-main.663
DOI:
10.18653/v1/2020.emnlp-main.663
Bibkey:
Cite (ACL):
Maryam Aminian, Mohammad Sadegh Rasooli, and Mona Diab. 2020. Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8268–8274, Online. Association for Computational Linguistics.
Cite (Informal):
Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies (Aminian et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2020.emnlp-main.663.pdf
Video:
 https://slideslive.com/38939217