{"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/improving-neural-parsing-by-disentangling","title":"Improving Neural Parsing by Disentangling Model Combination and Reranking Effects","arxiv_id":"1707.03058","date":"2017-07-10","proceeding":"ACL 2017 7","authors":["Daniel Fried","Mitchell Stern","Dan Klein"],"abstract":"Recent work has proposed several generative neural models for constituency\nparsing that achieve state-of-the-art results. Since direct search in these\ngenerative models is difficult, they have primarily been used to rescore\ncandidate outputs from base parsers in which decoding is more straightforward.\nWe first present an algorithm for direct search in these generative models. We\nthen demonstrate that the rescoring results are at least partly due to implicit\nmodel combination rather than reranking effects. Finally, we show that explicit\nmodel combination can improve performance even further, resulting in new\nstate-of-the-art numbers on the PTB of 94.25 F1 when training only on gold data\nand 94.66 F1 when using external data.","url_abs":"http://arxiv.org/abs/1707.03058v1","url_pdf":"http://arxiv.org/pdf/1707.03058v1.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":[],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"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":"Model combination","rank_in_archive_order":16,"of":27,"metrics":{"F1 score":"94.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.03058","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}