{"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/unpaired-sentiment-to-sentiment-translation-a","title":"Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach","arxiv_id":"1805.05181","date":"2018-05-14","proceeding":"ACL 2018 7","authors":["Jingjing Xu","Xu sun","Qi Zeng","Xuancheng Ren","Xiaodong Zhang","Houfeng Wang","Wenjie Li"],"abstract":"The goal of sentiment-to-sentiment \"translation\" is to change the underlying\nsentiment of a sentence while keeping its content. The main challenge is the\nlack of parallel data. To solve this problem, we propose a cycled reinforcement\nlearning method that enables training on unpaired data by collaboration between\na neutralization module and an emotionalization module. We evaluate our\napproach on two review datasets, Yelp and Amazon. Experimental results show\nthat our approach significantly outperforms the state-of-the-art systems.\nEspecially, the proposed method substantially improves the content preservation\nperformance. The BLEU score is improved from 1.64 to 22.46 and from 0.56 to\n14.06 on the two datasets, respectively.","url_abs":"http://arxiv.org/abs/1805.05181v2","url_pdf":"http://arxiv.org/pdf/1805.05181v2.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":"unpaired-sentiment-to-sentiment-translation-a","repo_url":"https://github.com/lancopku/unpaired-sentiment-translation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-style-transfoer","task_name":"Text Style Transfer"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.05181","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}