{"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/arc-swift-a-novel-transition-system-for","title":"Arc-swift: A Novel Transition System for Dependency Parsing","arxiv_id":"1705.04434","date":"2017-05-12","proceeding":"ACL 2017 7","authors":["Peng Qi","Christopher D. Manning"],"abstract":"Transition-based dependency parsers often need sequences of local shift and\nreduce operations to produce certain attachments. Correct individual decisions\nhence require global information about the sentence context and mistakes cause\nerror propagation. This paper proposes a novel transition system, arc-swift,\nthat enables direct attachments between tokens farther apart with a single\ntransition. This allows the parser to leverage lexical information more\ndirectly in transition decisions. Hence, arc-swift can achieve significantly\nbetter performance with a very small beam size. Our parsers reduce error by\n3.7--7.6% relative to those using existing transition systems on the Penn\nTreebank dependency parsing task and English Universal Dependencies.","url_abs":"http://arxiv.org/abs/1705.04434v1","url_pdf":"http://arxiv.org/pdf/1705.04434v1.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":"arc-swift-a-novel-transition-system-for","repo_url":"https://github.com/qipeng/arc-swift","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"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=1705.04434","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}