{"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/hybrid-oracle-making-use-of-ambiguity-in","title":"Hybrid Oracle: Making Use of Ambiguity in Transition-based Chinese Dependency Parsing","arxiv_id":"1711.10163","date":"2017-11-28","proceeding":null,"authors":["Xuancheng Ren","Xu sun"],"abstract":"In the training of transition-based dependency parsers, an oracle is used to\npredict a transition sequence for a sentence and its gold tree. However, the\ntransition system may exhibit ambiguity, that is, there can be multiple correct\ntransition sequences that form the gold tree. We propose to make use of the\nproperty in the training of neural dependency parsers, and present the Hybrid\nOracle. The new oracle gives all the correct transitions for a parsing state,\nwhich are used in the cross entropy loss function to provide better supervisory\nsignal. It is also used to generate different transition sequences for a\nsentence to better explore the training data and improve the generalization\nability of the parser. Evaluations show that the parsers trained using the\nhybrid oracle outperform the parsers using the traditional oracle in Chinese\ndependency parsing. We provide analysis from a linguistic view. The code is\navailable at https://github.com/lancopku/nndep .","url_abs":"http://arxiv.org/abs/1711.10163v2","url_pdf":"http://arxiv.org/pdf/1711.10163v2.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":"hybrid-oracle-making-use-of-ambiguity-in","repo_url":"https://github.com/lancopku/nndep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Chinese Dependency Parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}