{"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/global-transition-based-non-projective","title":"Global Transition-based Non-projective Dependency Parsing","arxiv_id":"1807.01745","date":"2018-07-04","proceeding":"ACL 2018 7","authors":["Carlos Gómez-Rodríguez","Tianze Shi","Lillian Lee"],"abstract":"Shi, Huang, and Lee (2017) obtained state-of-the-art results for English and\nChinese dependency parsing by combining dynamic-programming implementations of\ntransition-based dependency parsers with a minimal set of bidirectional LSTM\nfeatures. However, their results were limited to projective parsing. In this\npaper, we extend their approach to support non-projectivity by providing the\nfirst practical implementation of the MH_4 algorithm, an $O(n^4)$ mildly\nnonprojective dynamic-programming parser with very high coverage on\nnon-projective treebanks. To make MH_4 compatible with minimal transition-based\nfeature sets, we introduce a transition-based interpretation of it in which\nparser items are mapped to sequences of transitions. We thus obtain the first\nimplementation of global decoding for non-projective transition-based parsing,\nand demonstrate empirically that it is more effective than its projective\ncounterpart in parsing a number of highly non-projective languages","url_abs":"http://arxiv.org/abs/1807.01745v1","url_pdf":"http://arxiv.org/pdf/1807.01745v1.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":"global-transition-based-non-projective","repo_url":"https://github.com/tzshi/mh4-parser-acl18","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Chinese Dependency Parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}