{"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/end-to-end-graph-based-tag-parsing-with","title":"End-to-end Graph-based TAG Parsing with Neural Networks","arxiv_id":"1804.06610","date":"2018-04-18","proceeding":"NAACL 2018 6","authors":["Jungo Kasai","Robert Frank","Pauli Xu","William Merrill","Owen Rambow"],"abstract":"We present a graph-based Tree Adjoining Grammar (TAG) parser that uses\nBiLSTMs, highway connections, and character-level CNNs. Our best end-to-end\nparser, which jointly performs supertagging, POS tagging, and parsing,\noutperforms the previously reported best results by more than 2.2 LAS and UAS\npoints. The graph-based parsing architecture allows for global inference and\nrich feature representations for TAG parsing, alleviating the fundamental\ntrade-off between transition-based and graph-based parsing systems. We also\ndemonstrate that the proposed parser achieves state-of-the-art performance in\nthe downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and\nUnbounded Dependency Recovery. This provides further support for the claim that\nTAG is a viable formalism for problems that require rich structural analysis of\nsentences.","url_abs":"http://arxiv.org/abs/1804.06610v3","url_pdf":"http://arxiv.org/pdf/1804.06610v3.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":"end-to-end-graph-based-tag-parsing-with","repo_url":"https://github.com/jungokasai/graph_parser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.06610","atlas_url":"https://app.syntology.ai/?focus=1804.06610","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}