Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proc. AAAI Conf. Artif. Intell.

ISBN

—

ISSN

21595399

e-ISSN

—

Počet stran výsledku

9

Strana od-do

25119-25127

Název nakladatele

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

Místo vydání

—

Místo konání akce

Philadelphia

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—