{"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/neural-text-generation-from-rich-semantic","title":"Neural Text Generation from Rich Semantic Representations","arxiv_id":"1904.11564","date":"2019-04-25","proceeding":"NAACL 2019 6","authors":["Valerie Hajdik","Jan Buys","Michael W. Goodman","Emily M. Bender"],"abstract":"We propose neural models to generate high-quality text from structured\nrepresentations based on Minimal Recursion Semantics (MRS). MRS is a rich\nsemantic representation that encodes more precise semantic detail than other\nrepresentations such as Abstract Meaning Representation (AMR). We show that a\nsequence-to-sequence model that maps a linearization of Dependency MRS, a\ngraph-based representation of MRS, to English text can achieve a BLEU score of\n66.11 when trained on gold data. The performance can be improved further using\na high-precision, broad coverage grammar-based parser to generate a large\nsilver training corpus, achieving a final BLEU score of 77.17 on the full test\nset, and 83.37 on the subset of test data most closely matching the silver data\ndomain. Our results suggest that MRS-based representations are a good choice\nfor applications that need both structured semantics and the ability to produce\nnatural language text as output.","url_abs":"http://arxiv.org/abs/1904.11564v1","url_pdf":"http://arxiv.org/pdf/1904.11564v1.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":"neural-text-generation-from-rich-semantic","repo_url":"https://github.com/shlurbee/dmrs-text-generation-naacl2019","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"abstract-meaning-representation","task_name":"Abstract Meaning Representation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}