{"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/a-non-projective-greedy-dependency-parser","title":"A non-projective greedy dependency parser with bidirectional LSTMs","arxiv_id":"1707.03228","date":"2017-07-11","proceeding":"CONLL 2017 8","authors":["David Vilares","Carlos Gómez-Rodríguez"],"abstract":"The LyS-FASTPARSE team presents BIST-COVINGTON, a neural implementation of\nthe Covington (2001) algorithm for non-projective dependency parsing. The\nbidirectional LSTM approach by Kipperwasser and Goldberg (2016) is used to\ntrain a greedy parser with a dynamic oracle to mitigate error propagation. The\nmodel participated in the CoNLL 2017 UD Shared Task. In spite of not using any\nensemble methods and using the baseline segmentation and PoS tagging, the\nparser obtained good results on both macro-average LAS and UAS in the big\ntreebanks category (55 languages), ranking 7th out of 33 teams. In the all\ntreebanks category (LAS and UAS) we ranked 16th and 12th. The gap between the\nall and big categories is mainly due to the poor performance on four parallel\nPUD treebanks, suggesting that some `suffixed' treebanks (e.g. Spanish-AnCora)\nperform poorly on cross-treebank settings, which does not occur with the\ncorresponding `unsuffixed' treebank (e.g. Spanish). By changing that, we obtain\nthe 11th best LAS among all runs (official and unofficial). The code is made\navailable at https://github.com/CoNLL-UD-2017/LyS-FASTPARSE","url_abs":"http://arxiv.org/abs/1707.03228v1","url_pdf":"http://arxiv.org/pdf/1707.03228v1.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":"a-non-projective-greedy-dependency-parser","repo_url":"https://github.com/CoNLL-UD-2017/LyS-FASTPARSE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"}],"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}