Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
This work addresses robustness issues in unsupervised dependency parsing for NLP applications, representing an incremental improvement over existing ensemble methods.
The paper tackles the problem of error accumulation in ensembles for unsupervised dependency parsing by proposing an ensemble-selection method that considers error diversity, resulting in improved performance and robustness over individual models and previous ensemble techniques.
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.