[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85229-en":3,"doc-seo-85229-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85229,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Non-binary bottom-up constituency parsing without arity actions","Non-binary bottom-up constituency parsing is often implemented with arity actions, where reductions like REDUCE-X#k encode both the parent label and the number of children. This work shows that arity need not be an explicit transition primitive. The parser predicts constituent labels separately and derives reduction spans from delimiter-bounded stack configurations. In a well-formed reduction configuration, arity is uniquely determined from parser state rather than action labels. Experiments on PTB and CTB confirm competitive performance with smaller action inventories.","Non-binary bottom-up constituency parsing without arity actions  \nJungyeul Park* Eunkyul Leah Jo Zihao Huang  \n Korea Advanced Institute of Science & Technology, Daejeon, South Korea  The University of British Columbia, Vancouver, Canada  \n[https://ct.kaist.ac.kr](https://ct.kaist.ac.kr) [https://linguistics.ubc.ca](https://linguistics.ubc.ca)  \narXiv :2607 . 1059 1v 1 [ cs .CL] 12 Jul 2026  \nAbstract  \nNon-binary bottom-up constituency parsing is usually taken to require arity actions: reductions such as REDUCE-X\\#k specify both themother label and the number of children to be composed. We show that this arity parameter isnot 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 nonbinary 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.  \n1 Introduction  \nTransition-based constituency parsing builds phrase-structure trees through local actions over a stack and an input buffer. A central distinction among transition systems is how they make the boundary of an unfinished constituent available before the constituent is completed. In top-down parsing, the boundary is introduced by an open nonterminal (Dyer et al., 2016) . In in-order parsing, it is introduced by a projected nonterminal after the left corner has been shifted (Liu and Zhang, 2017a) . In purely bottom-up parsing, no such marker is inherent to the derivation: the parent label is introduced only after its children have already been recognized (Sagae and Lavie, 2005 ; Wang et al., 2006 ; Zhang  \n* Corresponding author.  \nand Clark, 2009 ; Zhu et al., 2013 ; Watanabe and Sumita, 2015 ; Liu and Zhang, 2017b ; FernándezGonzález and Gómez-Rodríguez, 2019) .  \nThis boundary problem is sharpened by nonbinary parsing. Traditional bottom-up systems avoid arbitrary reduction spans by binarizing the treebank, so that each reduction combines at most two stack items. Non-binary bottom-up parsing instead constructs original treebank constituents directly, avoiding the intermediate structure introduced by binarization. Existing systems achieve this by encoding both the mother label and the number of children in a single action, such as REDUCE-X\\#k (Fernández-González and GómezRodríguez, 2019) . In such a system, arity is an action-level decision: k specifies how many completed stack items are grouped under X. The transition inventory is therefore tied to the observed set of nonterminal–arity combinations.  \nWe propose a non-binary bottom-up constituency parser in which arity is not an explicit transition label. The parser separates label prediction from span determination. A constituent label is introduced by NT(X), while the reduction domain is recovered from delimiters placed on the stack. The operations D-SHIFT and D-REDUCE make bottom-up constituent boundaries available without requiring actions of the form REDUCE-X\\#k.  \nThe resulting system retains direct construction of arbitrary-arity constituents without binarization, but replaces arity classification with stack-based span recovery. Its central property is arity recoverability: in a well-formed delimiter-bounded reduction configuration, the number of children is uniquely determined by the completed stack items between the active delimiter and the label marker. Arity is thus an invaria","cbCaikWqhSVg5tgX","https://ap.wps.com/l/cbCaikWqhSVg5tgX","pdf",316193,1,13,"English","en",105,"# Introduction\n## Transition-based constituency parsing\n## Non-binary parsing background\n# Background\n## Transition-based constituency parsing","[{\"question\":\"Why do non-binary bottom-up constituency parsers often use arity actions like REDUCE-X#k?\",\"answer\":\"Because those systems encode both the mother label and the number of children inside a single reduction action, making k an action-level decision. This ties the transition inventory to the nonterminal–arity combinations.\"},{\"question\":\"How does the proposed parser avoid using arity as an explicit transition label?\",\"answer\":\"It separates constituent label prediction (e.g., NT(X)) from reduction span determination. Delimiters on the stack allow recovery of the reduction domain without actions of the form REDUCE-X#k.\"},{\"question\":\"What determines the number of children (arity) in the proposed method?\",\"answer\":\"In a well-formed delimiter-bounded reduction configuration, arity is uniquely determined by the active delimiter and the label marker, making it a derived invariant of parser state. Experiments show the predicted arity profile stays close to the gold treebanks and high-arity constituents are preserved.\"}]",1784201875,33,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"non-binary-bottom-up-constituency-parsing-without-arity-actions","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/non-binary-bottom-up-constituency-parsing-without-arity-actions/85229/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do non-binary bottom-up constituency parsers often use arity actions like REDUCE-X#k?","Question",{"text":75,"@type":76},"Because those systems encode both the mother label and the number of children inside a single reduction action, making k an action-level decision. This ties the transition inventory to the nonterminal–arity combinations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed parser avoid using arity as an explicit transition label?",{"text":80,"@type":76},"It separates constituent label prediction (e.g., NT(X)) from reduction span determination. Delimiters on the stack allow recovery of the reduction domain without actions of the form REDUCE-X#k.",{"name":82,"@type":73,"acceptedAnswer":83},"What determines the number of children (arity) in the proposed method?",{"text":84,"@type":76},"In a well-formed delimiter-bounded reduction configuration, arity is uniquely determined by the active delimiter and the label marker, making it a derived invariant of parser state. Experiments show the predicted arity profile stays close to the gold treebanks and high-arity constituents are preserved.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]