On the Relation between Syntactic Divergence and Zero-Shot Performance

Ofir Arviv*, Dmitry Nikolaev*, Taelin Karidi, Omri Abend

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

We explore the link between the extent to which syntactic relations are preserved in translation and the ease of correctly constructing a parse tree in a zero-shot setting. While previous work suggests such a relation, it tends to focus on the macro level and not on the level of individual edges-a gap we aim to address. As a test case, we take the transfer of Universal Dependencies (UD) parsing from English to a diverse set of languages and conduct two sets of experiments. In one, we analyze zero-shot performance based on the extent to which English source edges are preserved in translation. In another, we apply three linguistically motivated transformations to UD, creating more cross-lingually stable versions of it, and assess their zero-shot parsability. In order to compare parsing performance across different schemes, we perform extrinsic evaluation on the downstream task of cross-lingual relation extraction (RE) using a subset of a popular English RE benchmark translated to Russian and Korean. In both sets of experiments, our results suggest a strong relation between cross-lingual stability and zero-shot parsing performance.

Original languageEnglish
Title of host publicationEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages4803-4817
Number of pages15
ISBN (Electronic)9781955917094
StatePublished - 2021
Event2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 - Virtual, Punta Cana, Dominican Republic
Duration: 7 Nov 202111 Nov 2021

Publication series

NameEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Country/TerritoryDominican Republic
CityVirtual, Punta Cana
Period7/11/2111/11/21

Bibliographical note

Funding Information:
This work was supported by the Israel Science Foundation (grant no. 929/17). Taelin Karidi was partially supported by a fellowship from the Hebew University Center for Interdisciplinary Data Science Research.

Publisher Copyright:
© 2021 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'On the Relation between Syntactic Divergence and Zero-Shot Performance'. Together they form a unique fingerprint.

Cite this