{"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/span-based-constituency-parsing-with-a","title":"Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles","arxiv_id":"1612.06475","date":"2016-12-20","proceeding":"EMNLP 2016 11","authors":["James Cross","Liang Huang"],"abstract":"Parsing accuracy using efficient greedy transition systems has improved\ndramatically in recent years thanks to neural networks. Despite striking\nresults in dependency parsing, however, neural models have not surpassed\nstate-of-the-art approaches in constituency parsing. To remedy this, we\nintroduce a new shift-reduce system whose stack contains merely sentence spans,\nrepresented by a bare minimum of LSTM features. We also design the first\nprovably optimal dynamic oracle for constituency parsing, which runs in\namortized O(1) time, compared to O(n^3) oracles for standard dependency\nparsing. Training with this oracle, we achieve the best F1 scores on both\nEnglish and French of any parser that does not use reranking or external data.","url_abs":"http://arxiv.org/abs/1612.06475v1","url_pdf":"http://arxiv.org/pdf/1612.06475v1.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":"span-based-constituency-parsing-with-a","repo_url":"https://github.com/jhcross/span-parser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"sentence","task_name":"Sentence"}],"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=1612.06475","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}