Ensemble Distillation for Unsupervised Constituency Parsing

arXiv:2310.01717v2 Announce Type: replace-cross
Abstract: 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 …

abstract annotated data arxiv cs.ai cs.cl cs.lg data distillation ensemble hierarchical observe parsing performance type unsupervised words