Non-binary bottom-up constituency parsing without arity actions

• URL: http://arxiv.org/abs/2607.10591v1
• Date: Sun, 12 Jul 2026 06:07:29 GMT
• Title: Non-binary bottom-up constituency parsing without arity actions
• Abstract summary: We show that this arity parameter is not a necessary transition primitive.<n>We 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.
• Score: 8.373441227262644
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• A Symmetric Layer-Union Audit of Component Collapse in Hierarchical Procedural Corpora [0.0]
  Component-disjoint leakage control can group corpus units by content similarity, hierarchical membership, or both.<n>Guvenilir and Dogan previously showed that merging relation types can create a giant component that obstructs splitting.<n>We examine it through a symmetric audit of a content-near-duplicate layer, a common-container layer, and their union in a fixed panel of six hierarchical procedural corpora.
  arXiv  Detail & Related papers  (2026-08-09T20:13:17Z)
• Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition [1.3290717106567922]
  We exploit a shared key-value template $(S)U$ to develop Unpack, a backward recursion that decomposes credit through both sublayers.<n>On GPT-2 small, the method recovers all three composition connections described by Wang et al. (2023), including the mode-specific routing of each connection.<n>Across the Pythia family from 160M to 6.9B parameters, this suppression pattern is consistently recovered at every scale.
  arXiv  Detail & Related papers  (2026-05-22T09:03:01Z)
• BPC-Net: Annotation-Free Skin Lesion Segmentation via Boundary Probability Calibration [15.992042021607643]
  We propose BPC-Net, a boundary probability calibration framework for annotation-free skin lesion segmentation.<n>The proposed framework achieves state-of-the-art performance among published unsupervised methods, reaching a macro-average Dice coefficient and Jaccard index of 85.80% and 76.97%, respectively.
  arXiv  Detail & Related papers  (2026-04-07T08:43:34Z)
• PLESS: Pseudo-Label Enhancement with Spreading Scribbles for Weakly Supervised Segmentation [5.862480696321742]
  Weakly supervised learning with scribble annotations uses sparse user-drawn strokes to indicate segmentation labels on a small subset of pixels.<n>Recent scribble-based approaches in medical image segmentation address this limitation using pseudo-label-based training.<n>We propose PLESS, a generic pseudo-label enhancement strategy which improves reliability and spatial consistency.
  arXiv  Detail & Related papers  (2026-02-12T06:24:05Z)
• STRAP: Structured Object Affordance Segmentation with Point Supervision [20.56373848741831]
  We study affordance segmentation with point supervision, wherein the setting inherits an unexplored dual affinity-spatial affinity and label affinity. We devise a dense prediction network that enhances label relations by effectively densifying labels in a new domain. In experiments, we benchmark our method on the challenging CAD120 dataset, showing significant performance gains over prior methods.
  arXiv  Detail & Related papers  (2023-04-17T17:59:49Z)
• Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [98.66771688028426]
  We propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Joint-Confidence Estimation (JCE) is proposed to quantifies the classification and localization quality of pseudo labels. ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
  arXiv  Detail & Related papers  (2023-03-27T07:46:58Z)
• Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences [67.37544997614646]
  We present the first study on unsupervised spoken constituency parsing. The goal is to determine the spoken sentences' hierarchical syntactic structure in the form of constituency parse trees. We show that accurate segmentation alone may be sufficient to parse spoken sentences accurately.
  arXiv  Detail & Related papers  (2023-03-15T17:57:22Z)
• Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning [50.40482222266927]
  Referring Expression (RES) is aimed at localizing and segmenting the target according to the given language expression. We propose a parallel position- kernel-segmentation pipeline to better isolate and then interact with the localization and segmentation steps. Our method is simple but surprisingly effective, outperforming all previous state-of-the-art RES methods on fully- and weakly-supervised settings.
  arXiv  Detail & Related papers  (2022-12-17T08:29:33Z)
• Inducing and Using Alignments for Transition-based AMR Parsing [51.35194383275297]
  We propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.
  arXiv  Detail & Related papers  (2022-05-03T12:58:36Z)
• Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation [141.16965264264195]
  Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained supervisions. We propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels.
  arXiv  Detail & Related papers  (2022-03-21T05:16:23Z)
• Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence [48.69930912510414]
  We propose an unsupervised and training-free labeling procedure by exploiting the property of a recently introduced metric. For implementation, we develop NDD into Dual POS-NDD and build "molds" to detect constituents and their labels in sentences. We show that DP-NDD not only labels constituents precisely but also inducts more accurate unlabeled constituency trees than all previous unsupervised methods with simpler rules.
  arXiv  Detail & Related papers  (2021-10-29T17:27:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.