{"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/end-to-end-content-and-plan-selection-for","title":"End-to-End Content and Plan Selection for Data-to-Text Generation","arxiv_id":"1810.04700","date":"2018-10-10","proceeding":"WS 2018 11","authors":["Sebastian Gehrmann","Falcon Z. Dai","Henry Elder","Alexander M. Rush"],"abstract":"Learning to generate fluent natural language from structured data with neural\nnetworks has become an common approach for NLG. This problem can be challenging\nwhen the form of the structured data varies between examples. This paper\npresents a survey of several extensions to sequence-to-sequence models to\naccount for the latent content selection process, particularly variants of copy\nattention and coverage decoding. We further propose a training method based on\ndiverse ensembling to encourage models to learn distinct sentence templates\nduring training. An empirical evaluation of these techniques shows an increase\nin the quality of generated text across five automated metrics, as well as\nhuman evaluation.","url_abs":"http://arxiv.org/abs/1810.04700v1","url_pdf":"http://arxiv.org/pdf/1810.04700v1.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":"end-to-end-content-and-plan-selection-for","repo_url":"https://github.com/sebastianGehrmann/diverse_ensembling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1810.04700","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}