Non-binary bottom-up constituency parsing without arity actions
Abstract
Non-binary bottom-up constituency parsing is usually taken to require arity actions: reductions such as specify both the mother label and the number of children to be composed. We show that this arity parameter is not a necessary transition primitive. Our parser introduces constituent labels separately and recovers reduction spans from delimiter-bounded stack configurations. In a well-formed reduction configuration, arity is uniquely determined by the active delimiter and the label marker, making it a derived property of parser state rather than an action label. This factorization removes label--arity-specific reduce actions while preserving direct construction of original non-binary trees. Experiments on PTB and CTB show that the delimiter-guided parser remains competitive with an arity-specific bottom-up baseline under the same implementation framework, with substantially smaller action inventories. Analyses further show that its predicted arity profile remains close to the gold treebanks and that high-arity constituents do not collapse when arity actions are removed.
Cite
@article{arxiv.2607.10591,
title = {Non-binary bottom-up constituency parsing without arity actions},
author = {Jungyeul Park and Eunkyul Leah Jo and Zihao Huang},
journal= {arXiv preprint arXiv:2607.10591},
year = {2026}
}