通过考虑错误多样性，提升无监督依存句法分析集成模型的鲁棒性。
Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
- 后处理聚合多个模型输出，选择错误模式不同的组件以减少误差累积。
- 在多个数据集上超越单个模型及现有集成方法，性能提升显著。
- 适合追求高鲁棒性的无监督句法分析研究者使用。
我们通过后处理聚合现有模型的依存句法结构构建集成模型来解决无监督依存句法分析问题。观察发现，此类集成常因弱组件导致误差累积而表现出低鲁棒性。为此，我们提出一种高效的集成选择方法，考虑错误多样性并避免误差累积。实验表明，该方法优于每个单个模型以及先前的集成技术。此外，实验还显示，所提方法显著提升了集成的性能与鲁棒性，超越了未考虑错误多样性的以往策略。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。