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

Autor:	Shayegh, Behzad, Lee, Hobie H. -B., Zhu, Xiaodan, Cheung, Jackie Chi Kit, Mou, Lili
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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 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. Comment: Accepted by the AAAI Conference on Artificial Intelligence (AAAI) 2025
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.11543 Zobrazit plný text záznamu View this record from Arxiv