cs.CLJul 12, 2026

Non-binary bottom-up constituency parsing without arity actions

Authors: Jungyeul ParkEunkyul Leah JoZihao Huang

Organizations: Korea Advanced Institute of Science & Technology, Daejeon, South Korea · The University of British Columbia, Vancouver, Canada

Abstract

Non-binary bottom-up constituency parsing is usually taken to require arity actions: reductions such as \textscReduceX#k\textsc{Reduce-}X\#k 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.

Explore similar work

CardsList
  1. Prefix Parsing is Just Parsing

    Apr 23, 2026Clemente Pasti, Andreas Opedal, Timothy J. O'Donnell +2Context-Free GrammarsNext-Token Prediction