{"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/unsupervised-controllable-text-formalization","title":"Unsupervised Controllable Text Formalization","arxiv_id":"1809.04556","date":"2018-09-10","proceeding":null,"authors":["Parag Jain","Abhijit Mishra","Amar Prakash Azad","Karthik Sankaranarayanan"],"abstract":"We propose a novel framework for controllable natural language\ntransformation. Realizing that the requirement of parallel corpus is\npractically unsustainable for controllable generation tasks, an unsupervised\ntraining scheme is introduced. The crux of the framework is a deep neural\nencoder-decoder that is reinforced with text-transformation knowledge through\nauxiliary modules (called scorers). The scorers, based on off-the-shelf\nlanguage processing tools, decide the learning scheme of the encoder-decoder\nbased on its actions. We apply this framework for the text-transformation task\nof formalizing an input text by improving its readability grade; the degree of\nrequired formalization can be controlled by the user at run-time. Experiments\non public datasets demonstrate the efficacy of our model towards: (a)\ntransforming a given text to a more formal style, and (b) introducing\nappropriate amount of formalness in the output text pertaining to the input\ncontrol. Our code and datasets are released for academic use.","url_abs":"http://arxiv.org/abs/1809.04556v6","url_pdf":"http://arxiv.org/pdf/1809.04556v6.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":"unsupervised-controllable-text-formalization","repo_url":"https://github.com/parajain/uctf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.04556","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}