Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AU5QG6UFW" target="_blank" >RIV/00216208:11320/26:U5QG6UFW - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1609/aaai.v39i23.34697" target="_blank" >http://dx.doi.org/10.1609/aaai.v39i23.34697</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/aaai.v39i23.34697" target="_blank" >10.1609/aaai.v39i23.34697</a>
Alternative languages
Result language
angličtina
Original language name
Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
Original language description
We address unsupervised dependency parsing by building an ensemble of diverse existing models through post hoc aggregation of their output dependency parse structures. We observe that these ensembles often suffer from low robustness against weak ensemble components due to error accumulation. To tackle this problem, we propose an efficient ensemble-selection approach that considers error diversity and avoids error accumulation. Results demonstrate that our approach outperforms each individual model as well as previous ensemble techniques. Additionally, our experiments show that the proposed ensemble-selection method significantly enhances the performance and robustness of our ensemble, surpassing previously proposed strategies, which have not accounted for error diversity. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
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
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proc. AAAI Conf. Artif. Intell.
ISBN
—
ISSN
21595399
e-ISSN
—
Number of pages
9
Pages from-to
25119-25127
Publisher name
39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
Place of publication
—
Event location
Philadelphia
Event date
Jan 1, 2026
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—