Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AQLM25E7J" target="_blank" >RIV/00216208:11320/25:QLM25E7J - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2024.mwe-1.10.pdf" target="_blank" >https://aclanthology.org/2024.mwe-1.10.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2021.iwpt-1.9" target="_blank" >10.18653/v1/2021.iwpt-1.9</a>
Alternative languages
Result language
angličtina
Original language name
Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing
Original language description
UDify (Kondratyuk and Straka, 2019) is a multilingual and multi-task parser fine-tuned on mBERT that achieves remarkable performance in high-resource languages. However, the performance saturates early and decreases gradually in low-resource languages as training proceeds. This work applies a data augmentation method and conducts experiments on seven few-shot and four zero-shot languages. The unlabeled attachment scores were improved on the zero-shot languages dependency parsing tasks, with the average score rising from 67.1% to 68.7%. Meanwhile, dependency parsing tasks for high-resource languages and other tasks were hardly affected. Experimental results indicate the data augmentation method is effective for low-resource languages in a multilingual dependency parsing.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD)@ LREC-COLING 2024
ISBN
978-2-493-81420-3
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
63-69
Publisher name
ACL
Place of publication
—
Event location
Torino, Italia
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—