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，该任务旨在无需依赖语言标注数据的情况下，将句子中的单词和短语组织成层次化结构。我们观察到，现有无监督句法分析器捕捉了句法结构的不同方面，这一特性可用于提升无监督句法分析的性能。为此，我们提出了“树平均”概念，并在此基础上进一步提出了一种新颖的无监督句法集成方法。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平滑问题。实验表明，我们的方法超越了以往所有方法，并在多次运行、不同集成组件以及领域迁移条件下，始终展现出其有效性及稳健性。