{"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/amr-parsing-as-sequence-to-graph-transduction","title":"AMR Parsing as Sequence-to-Graph Transduction","arxiv_id":"1905.08704","date":"2019-05-21","proceeding":"ACL 2019 7","authors":["Sheng Zhang","Xutai Ma","Kevin Duh","Benjamin Van Durme"],"abstract":"We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is aligner-free, and it can be effectively trained with limited amounts of labeled AMR data. Our experimental results outperform all previously reported SMATCH scores, on both AMR 2.0 (76.3% F1 on LDC2017T10) and AMR 1.0 (70.2% F1 on LDC2014T12).","url_abs":"https://arxiv.org/abs/1905.08704v2","url_pdf":"https://arxiv.org/pdf/1905.08704v2.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":"amr-parsing-as-sequence-to-graph-transduction","repo_url":"https://github.com/sheng-z/stog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/amr-parsing-on-ldc2014t12-1","task":"AMR Parsing","dataset":"LDC2014T12","model":"Two-stage Sequence-to-Graph Transducer","rank_in_archive_order":5,"of":12,"metrics":{"F1 Full":"70.2"},"uses_additional_data":false},{"leaderboard":"/sota/amr-parsing-on-ldc2014t12","task":"AMR Parsing","dataset":"LDC2014T12:","model":"Sequence-to-Graph Transduction","rank_in_archive_order":1,"of":5,"metrics":{"F1 Full":"0.70","F1 Newswire":"0.75"},"uses_additional_data":false},{"leaderboard":"/sota/amr-parsing-on-ldc2017t10","task":"AMR Parsing","dataset":"LDC2017T10","model":"Sequence-to-Graph Transduction","rank_in_archive_order":21,"of":27,"metrics":{"Smatch":"76.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.08704","atlas_url":"https://app.syntology.ai/?focus=1905.08704","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}