{"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/content-preserving-text-generation-with","title":"Content preserving text generation with attribute controls","arxiv_id":"1811.01135","date":"2018-11-03","proceeding":"NeurIPS 2018 12","authors":["Lajanugen Logeswaran","Honglak Lee","Samy Bengio"],"abstract":"In this work, we address the problem of modifying textual attributes of\nsentences. Given an input sentence and a set of attribute labels, we attempt to\ngenerate sentences that are compatible with the conditioning information. To\nensure that the model generates content compatible sentences, we introduce a\nreconstruction loss which interpolates between auto-encoding and\nback-translation loss components. We propose an adversarial loss to enforce\ngenerated samples to be attribute compatible and realistic. Through\nquantitative, qualitative and human evaluations we demonstrate that our model\nis capable of generating fluent sentences that better reflect the conditioning\ninformation compared to prior methods. We further demonstrate that the model is\ncapable of simultaneously controlling multiple attributes.","url_abs":"http://arxiv.org/abs/1811.01135v1","url_pdf":"http://arxiv.org/pdf/1811.01135v1.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":"content-preserving-text-generation-with","repo_url":"https://github.com/hwijeen/CPTG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.01135","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}