{"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/bi-directional-attention-with-agreement-for","title":"Bi-directional Attention with Agreement for Dependency Parsing","arxiv_id":"1608.02076","date":"2016-08-06","proceeding":"EMNLP 2016 11","authors":["Hao Cheng","Hao Fang","Xiaodong He","Jianfeng Gao","Li Deng"],"abstract":"We develop a novel bi-directional attention model for dependency parsing,\nwhich learns to agree on headword predictions from the forward and backward\nparsing directions. The parsing procedure for each direction is formulated as\nsequentially querying the memory component that stores continuous headword\nembeddings. The proposed parser makes use of {\\it soft} headword embeddings,\nallowing the model to implicitly capture high-order parsing history without\ndramatically increasing the computational complexity. We conduct experiments on\nEnglish, Chinese, and 12 other languages from the CoNLL 2006 shared task,\nshowing that the proposed model achieves state-of-the-art unlabeled attachment\nscores on 6 languages.","url_abs":"http://arxiv.org/abs/1608.02076v2","url_pdf":"http://arxiv.org/pdf/1608.02076v2.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":"bi-directional-attention-with-agreement-for","repo_url":"https://github.com/hao-cheng/biattdp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"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}