We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data. We observe that existing unsupervised parsers capture differing aspects of parsing structures, which can be leveraged to enhance unsupervised parsing performance. To this end, we propose a notion of "tree averaging," based on which we further propose a novel ensemble method for unsupervised parsing. To improve inference efficiency, we further distill the ensemble knowledge into a student model; such an ensemble-then-distill process is an effective approach to mitigate the over-smoothing problem existing in common multi-teacher distilling methods. Experiments show that our method surpasses all previous approaches, consistently demonstrating its effectiveness and robustness across various runs, with different ensemble components, and under domain-shift conditions.

翻译：我们研究了无监督成分句法分析任务，该任务旨在无需语言标注数据的情况下，将句子中的词语和短语组织成层次结构。我们观察到，现有无监督分析器捕捉了句法结构的不同方面，这可用于提升无监督分析的性能。为此，我们提出了“树平均”的概念，并基于此进一步提出了一种面向无监督分析的新型集成方法。为提升推理效率，我们将集成知识蒸馏至学生模型；这种“先集成后蒸馏”的过程有效缓解了常见多教师蒸馏方法中存在的过度平滑问题。实验表明，我们的方法超越了所有先前的方法，在不同运行、不同集成组件以及领域迁移条件下，均一致展现了其有效性和鲁棒性。