On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling

4Citations
Citations of this article
53Readers
Mendeley users who have this article in their library.

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 cross-lingual 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.

Cite

CITATION STYLE

APA

Zhang, Z., Strubell, E., & Hovy, E. (2021). On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling. In EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 6229–6246). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.emnlp-main.503

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free