{"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/toward-controlled-generation-of-text","title":"Toward Controlled Generation of Text","arxiv_id":"1703.00955","date":"2017-03-02","proceeding":"ICML 2017 8","authors":["Zhiting Hu","Zichao Yang","Xiaodan Liang","Ruslan Salakhutdinov","Eric P. Xing"],"abstract":"Generic generation and manipulation of text is challenging and has limited\nsuccess compared to recent deep generative modeling in visual domain. This\npaper aims at generating plausible natural language sentences, whose attributes\nare dynamically controlled by learning disentangled latent representations with\ndesignated semantics. We propose a new neural generative model which combines\nvariational auto-encoders and holistic attribute discriminators for effective\nimposition of semantic structures. With differentiable approximation to\ndiscrete text samples, explicit constraints on independent attribute controls,\nand efficient collaborative learning of generator and discriminators, our model\nlearns highly interpretable representations from even only word annotations,\nand produces realistic sentences with desired attributes. Quantitative\nevaluation validates the accuracy of sentence and attribute generation.","url_abs":"http://arxiv.org/abs/1703.00955v4","url_pdf":"http://arxiv.org/pdf/1703.00955v4.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":"toward-controlled-generation-of-text","repo_url":"https://github.com/asyml/texar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"toward-controlled-generation-of-text","repo_url":"https://github.com/asyml/texar/tree/master/examples/text_style_transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"toward-controlled-generation-of-text","repo_url":"https://github.com/omidkashefi/contrapositive-inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.00955","atlas_url":"https://app.syntology.ai/?focus=1703.00955","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}