{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dependency-parsing-as-head-selection","title":"Dependency Parsing as Head Selection","arxiv_id":"1606.01280","date":"2016-06-03","proceeding":"EACL 2017 4","authors":["Xingxing Zhang","Jianpeng Cheng","Mirella Lapata"],"abstract":"Conventional graph-based dependency parsers guarantee a tree structure both\nduring training and inference. Instead, we formalize dependency parsing as the\nproblem of independently selecting the head of each word in a sentence. Our\nmodel which we call \\textsc{DeNSe} (as shorthand for {\\bf De}pendency {\\bf\nN}eural {\\bf Se}lection) produces a distribution over possible heads for each\nword using features obtained from a bidirectional recurrent neural network.\nWithout enforcing structural constraints during training, \\textsc{DeNSe}\ngenerates (at inference time) trees for the overwhelming majority of sentences,\nwhile non-tree outputs can be adjusted with a maximum spanning tree algorithm.\nWe evaluate \\textsc{DeNSe} on four languages (English, Chinese, Czech, and\nGerman) with varying degrees of non-projectivity. Despite the simplicity of the\napproach, our parsers are on par with the state of the art.","url_abs":"http://arxiv.org/abs/1606.01280v4","url_pdf":"http://arxiv.org/pdf/1606.01280v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dependency-parsing-as-head-selection","repo_url":"https://github.com/XingxingZhang/dense_parser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.01280","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}