{"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/two-local-models-for-neural-constituent","title":"Two Local Models for Neural Constituent Parsing","arxiv_id":"1808.04850","date":"2018-08-14","proceeding":"COLING 2018 8","authors":["Zhiyang Teng","Yue Zhang"],"abstract":"Non-local features have been exploited by syntactic parsers for capturing\ndependencies between sub output structures. Such features have been a key to\nthe success of state-of-the-art statistical parsers. With the rise of deep\nlearning, however, it has been shown that local output decisions can give\nhighly competitive accuracies, thanks to the power of dense neural input\nrepresentations that embody global syntactic information. We investigate two\nconceptually simple local neural models for constituent parsing, which make\nlocal decisions to constituent spans and CFG rules, respectively. Consistent\nwith previous findings along the line, our best model gives highly competitive\nresults, achieving the labeled bracketing F1 scores of 92.4% on PTB and 87.3%\non CTB 5.1.","url_abs":"http://arxiv.org/abs/1808.04850v2","url_pdf":"http://arxiv.org/pdf/1808.04850v2.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":"two-local-models-for-neural-constituent","repo_url":"https://github.com/zeeeyang/two-local-neural-conparsers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.04850","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}