Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908327679623168 |
|---|---|
| author | Shayegh, Behzad Lee, Hobie H. -B. Zhu, Xiaodan Cheung, Jackie Chi Kit Mou, Lili |
| author_facet | Shayegh, Behzad Lee, Hobie H. -B. Zhu, Xiaodan Cheung, Jackie Chi Kit Mou, Lili |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11543 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing Shayegh, Behzad Lee, Hobie H. -B. Zhu, Xiaodan Cheung, Jackie Chi Kit Mou, Lili Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.11543 |