{"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/global-neural-ccg-parsing-with-optimality","title":"Global Neural CCG Parsing with Optimality Guarantees","arxiv_id":"1607.01432","date":"2016-07-05","proceeding":"EMNLP 2016 11","authors":["Kenton Lee","Mike Lewis","Luke Zettlemoyer"],"abstract":"We introduce the first global recursive neural parsing model with optimality\nguarantees during decoding. To support global features, we give up dynamic\nprograms and instead search directly in the space of all possible subtrees.\nAlthough this space is exponentially large in the sentence length, we show it\nis possible to learn an efficient A* parser. We augment existing parsing\nmodels, which have informative bounds on the outside score, with a global model\nthat has loose bounds but only needs to model non-local phenomena. The global\nmodel is trained with a new objective that encourages the parser to explore a\ntiny fraction of the search space. The approach is applied to CCG parsing,\nimproving state-of-the-art accuracy by 0.4 F1. The parser finds the optimal\nparse for 99.9% of held-out sentences, exploring on average only 190 subtrees.","url_abs":"http://arxiv.org/abs/1607.01432v2","url_pdf":"http://arxiv.org/pdf/1607.01432v2.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":"global-neural-ccg-parsing-with-optimality","repo_url":"https://github.com/kentonl/neuralccg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1607.01432","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}