{"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/a-graph-to-sequence-model-for-amr-to-text","title":"A Graph-to-Sequence Model for AMR-to-Text Generation","arxiv_id":"1805.02473","date":"2018-05-07","proceeding":"ACL 2018 7","authors":["Linfeng Song","Yue Zhang","Zhiguo Wang","Daniel Gildea"],"abstract":"The problem of AMR-to-text generation is to recover a text representing the\nsame meaning as an input AMR graph. The current state-of-the-art method uses a\nsequence-to-sequence model, leveraging LSTM for encoding a linearized AMR\nstructure. Although being able to model non-local semantic information, a\nsequence LSTM can lose information from the AMR graph structure, and thus faces\nchallenges with large graphs, which result in long sequences. We introduce a\nneural graph-to-sequence model, using a novel LSTM structure for directly\nencoding graph-level semantics. On a standard benchmark, our model shows\nsuperior results to existing methods in the literature.","url_abs":"http://arxiv.org/abs/1805.02473v3","url_pdf":"http://arxiv.org/pdf/1805.02473v3.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":"a-graph-to-sequence-model-for-amr-to-text","repo_url":"https://github.com/freesunshine0316/neural-graph-to-seq-mp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"amr-to-text-generation","task_name":"AMR-to-Text Generation"},{"task_slug":"graph-to-sequence","task_name":"Graph-to-Sequence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-to-sequence-on-ldc2015e86","task":"Graph-to-Sequence","dataset":"LDC2015E86:","model":"GRN","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"33.6"},"uses_additional_data":true},{"leaderboard":"/sota/text-generation-on-ldc2016e25","task":"Text Generation","dataset":"LDC2016E25","model":"Graph2Seq","rank_in_archive_order":1,"of":1,"metrics":{"BLEU":"22"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02473","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}