{"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/an-amr-aligner-tuned-by-transition-based","title":"An AMR Aligner Tuned by Transition-based Parser","arxiv_id":"1810.03541","date":"2018-10-08","proceeding":"EMNLP 2018 10","authors":["Yijia Liu","Wanxiang Che","Bo Zheng","Bing Qin","Ting Liu"],"abstract":"In this paper, we propose a new rich resource enhanced AMR aligner which\nproduces multiple alignments and a new transition system for AMR parsing along\nwith its oracle parser. Our aligner is further tuned by our oracle parser via\npicking the alignment that leads to the highest-scored achievable AMR graph.\nExperimental results show that our aligner outperforms the rule-based aligner\nin previous work by achieving higher alignment F1 score and consistently\nimproving two open-sourced AMR parsers. Based on our aligner and transition\nsystem, we develop a transition-based AMR parser that parses a sentence into\nits AMR graph directly. An ensemble of our parsers with only words and POS tags\nas input leads to 68.4 Smatch F1 score.","url_abs":"http://arxiv.org/abs/1810.03541v1","url_pdf":"http://arxiv.org/pdf/1810.03541v1.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":"an-amr-aligner-tuned-by-transition-based","repo_url":"https://github.com/Oneplus/tamr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/amr-parsing-on-ldc2014t12-1","task":"AMR Parsing","dataset":"LDC2014T12","model":"Transition-based+improved aligner+ensemble","rank_in_archive_order":6,"of":12,"metrics":{"F1 Full":"68.4","F1 Newswire":"73.3"},"uses_additional_data":false},{"leaderboard":"/sota/amr-parsing-on-ldc2014t12","task":"AMR Parsing","dataset":"LDC2014T12:","model":"Transition-based+improved aligner+ensemble","rank_in_archive_order":2,"of":5,"metrics":{"F1 Full":"0.68","F1 Newswire":"0.73"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.03541","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}