Non-binary bottom-up constituency parsing without arity actions
2026-07-12 • Computation and Language
Computation and Language
AI summaryⓘ
The authors explore a method for building sentence structures in parsing without needing a special action that tells exactly how many parts to combine at once (arity). Instead, their parser uses labels and stack markers to figure out the structure as it goes, making the number of combined parts a result of the process rather than an input action. This new approach simplifies the actions needed while still successfully creating correct sentence trees. Tests on standard datasets show their method works about as well as older methods but with fewer steps and complexity.
non-binary bottom-up parsingconstituency parsingarityreduce actionsparser statedelimiterstack configurationsPenn Treebank (PTB)Chinese Treebank (CTB)
Authors
Jungyeul Park, Eunkyul Leah Jo, Zihao Huang
Abstract
Non-binary bottom-up constituency parsing is usually taken to require arity actions: reductions such as \(\textsc{Reduce-}X\#k\) 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.