{"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/thank-you-bart-rewarding-pre-trained-models","title":"Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer","arxiv_id":"2105.06947","date":"2021-05-14","proceeding":"ACL 2021 5","authors":["Huiyuan Lai","Antonio Toral","Malvina Nissim"],"abstract":"Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to-sequence (BART) models boosts content preservation, and that this is possible even with limited amounts of parallel data. Augmenting these models with rewards that target style and content -- the two core aspects of the task -- we achieve a new state-of-the-art.","url_abs":"https://arxiv.org/abs/2105.06947v2","url_pdf":"https://arxiv.org/pdf/2105.06947v2.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":"thank-you-bart-rewarding-pre-trained-models","repo_url":"https://github.com/laihuiyuan/Pre-trained-formality-transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"formality-style-transfer","task_name":"Formality Style Transfer"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.06947","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}