Abstract
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervised SRL training data are not abundant. Cross-lingual learning can improve performance in this setting by transferring knowledge from high-resource languages to low-resource ones. Moreover, we hypothesize that annotations of syntactic dependencies can be leveraged to further facilitate cross-lingual transfer. In this work, we perform an empirical exploration of the helpfulness of syntactic supervision for crosslingual SRL within a simple multitask learning scheme. With comprehensive evaluations across ten languages (in addition to English) and three SRL benchmark datasets, including both dependency- and span-based SRL, we show the effectiveness of syntactic supervision in low-resource scenarios.- Anthology ID:
- 2021.emnlp-main.503
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6229–6246
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.503
- DOI:
- 10.18653/v1/2021.emnlp-main.503
- Cite (ACL):
- Zhisong Zhang, Emma Strubell, and Eduard Hovy. 2021. On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6229–6246, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling (Zhang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.emnlp-main.503.pdf
- Code
- zzsfornlp/zmsp
- Data
- Universal Dependencies