{"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/left-to-right-dependency-parsing-with-pointer","title":"Left-to-Right Dependency Parsing with Pointer Networks","arxiv_id":"1903.08445","date":"2019-03-20","proceeding":null,"authors":["Daniel Fernández-González","Carlos Gómez-Rodríguez"],"abstract":"We propose a novel transition-based algorithm that straightforwardly parses\nsentences from left to right by building $n$ attachments, with $n$ being the\nlength of the input sentence. Similarly to the recent stack-pointer parser by\nMa et al. (2018), we use the pointer network framework that, given a word, can\ndirectly point to a position from the sentence. However, our left-to-right\napproach is simpler than the original top-down stack-pointer parser (not\nrequiring a stack) and reduces transition sequence length in half, from 2$n$-1\nactions to $n$. This results in a quadratic non-projective parser that runs\ntwice as fast as the original while achieving the best accuracy to date on the\nEnglish PTB dataset (96.04% UAS, 94.43% LAS) among fully-supervised\nsingle-model dependency parsers, and improves over the former top-down\ntransition system in the majority of languages tested.","url_abs":"http://arxiv.org/abs/1903.08445v1","url_pdf":"http://arxiv.org/pdf/1903.08445v1.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":"left-to-right-dependency-parsing-with-pointer","repo_url":"https://github.com/danifg/Left2Right-Pointer-Parser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"left-to-right-dependency-parsing-with-pointer","repo_url":"https://github.com/danifg/SyntacticPointer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointer-net","method_name":"Pointer Network"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-penn-treebank","task":"Dependency Parsing","dataset":"Penn Treebank","model":"Left-to-Right Pointer Network","rank_in_archive_order":11,"of":22,"metrics":{"LAS":"94.43","UAS":"96.04"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.08445","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}