{"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/in-order-transition-based-constituent-parsing","title":"In-Order Transition-based Constituent Parsing","arxiv_id":"1707.05000","date":"2017-07-17","proceeding":"TACL 2017 1","authors":["Jiangming Liu","Yue Zhang"],"abstract":"Both bottom-up and top-down strategies have been used for neural\ntransition-based constituent parsing. The parsing strategies differ in terms of\nthe order in which they recognize productions in the derivation tree, where\nbottom-up strategies and top-down strategies take post-order and pre-order\ntraversal over trees, respectively. Bottom-up parsers benefit from rich\nfeatures from readily built partial parses, but lack lookahead guidance in the\nparsing process; top-down parsers benefit from non-local guidance for local\ndecisions, but rely on a strong encoder over the input to predict a constituent\nhierarchy before its construction.To mitigate both issues, we propose a novel\nparsing system based on in-order traversal over syntactic trees, designing a\nset of transition actions to find a compromise between bottom-up constituent\ninformation and top-down lookahead information. Based on stack-LSTM, our\npsycholinguistically motivated constituent parsing system achieves 91.8 F1 on\nWSJ benchmark. Furthermore, the system achieves 93.6 F1 with supervised\nreranking and 94.2 F1 with semi-supervised reranking, which are the best\nresults on the WSJ benchmark.","url_abs":"http://arxiv.org/abs/1707.05000v1","url_pdf":"http://arxiv.org/pdf/1707.05000v1.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":"in-order-transition-based-constituent-parsing","repo_url":"https://github.com/LeonCrashCode/InOrderParser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"in-order-transition-based-constituent-parsing","repo_url":"https://github.com/hantek/distance-parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reranking","task_name":"Reranking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/constituency-parsing-on-penn-treebank","task":"Constituency Parsing","dataset":"Penn Treebank","model":"In-order","rank_in_archive_order":19,"of":27,"metrics":{"F1 score":"94.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.05000","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}