{"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/toward-abstractive-summarization-using","title":"Toward Abstractive Summarization Using Semantic Representations","arxiv_id":"1805.10399","date":"2018-05-25","proceeding":"HLT 2015 5","authors":["Fei Liu","Jeffrey Flanigan","Sam Thomson","Norman Sadeh","Noah A. Smith"],"abstract":"We present a novel abstractive summarization framework that draws on the\nrecent development of a treebank for the Abstract Meaning Representation (AMR).\nIn this framework, the source text is parsed to a set of AMR graphs, the graphs\nare transformed into a summary graph, and then text is generated from the\nsummary graph. We focus on the graph-to-graph transformation that reduces the\nsource semantic graph into a summary graph, making use of an existing AMR\nparser and assuming the eventual availability of an AMR-to-text generator. The\nframework is data-driven, trainable, and not specifically designed for a\nparticular domain. Experiments on gold-standard AMR annotations and system\nparses show promising results. Code is available at:\nhttps://github.com/summarization","url_abs":"http://arxiv.org/abs/1805.10399v1","url_pdf":"http://arxiv.org/pdf/1805.10399v1.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":"toward-abstractive-summarization-using","repo_url":"https://github.com/summarization/semantic_summ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"abstract-meaning-representation","task_name":"Abstract Meaning Representation"},{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.10399","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}