{"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/faster-exact-decoding-and-global-training-for","title":"Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set","arxiv_id":"1708.09403","date":"2017-08-30","proceeding":"EMNLP 2017 9","authors":["Tianze Shi","Liang Huang","Lillian Lee"],"abstract":"We first present a minimal feature set for transition-based dependency\nparsing, continuing a recent trend started by Kiperwasser and Goldberg (2016a)\nand Cross and Huang (2016a) of using bi-directional LSTM features. We plug our\nminimal feature set into the dynamic-programming framework of Huang and Sagae\n(2010) and Kuhlmann et al. (2011) to produce the first implementation of\nworst-case O(n^3) exact decoders for arc-hybrid and arc-eager transition\nsystems. With our minimal features, we also present O(n^3) global training\nmethods. Finally, using ensembles including our new parsers, we achieve the\nbest unlabeled attachment score reported (to our knowledge) on the Chinese\nTreebank and the \"second-best-in-class\" result on the English Penn Treebank.","url_abs":"http://arxiv.org/abs/1708.09403v1","url_pdf":"http://arxiv.org/pdf/1708.09403v1.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":"faster-exact-decoding-and-global-training-for","repo_url":"https://github.com/tzshi/dp-parser-emnlp17","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"transition-based-dependency-parsing","task_name":"Transition-Based Dependency Parsing"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.09403","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}