{"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/a-reinforcement-learning-approach-to","title":"A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation","arxiv_id":"1805.01553","date":"2018-05-03","proceeding":null,"authors":["Tsz Kin Lam","Julia Kreutzer","Stefan Riezler"],"abstract":"We present an approach to interactive-predictive neural machine translation\nthat attempts to reduce human effort from three directions: Firstly, instead of\nrequiring humans to select, correct, or delete segments, we employ the idea of\nlearning from human reinforcements in form of judgments on the quality of\npartial translations. Secondly, human effort is further reduced by using the\nentropy of word predictions as uncertainty criterion to trigger feedback\nrequests. Lastly, online updates of the model parameters after every\ninteraction allow the model to adapt quickly. We show in simulation experiments\nthat reward signals on partial translations significantly improve character\nF-score and BLEU compared to feedback on full translations only, while human\neffort can be reduced to an average number of $5$ feedback requests for every\ninput.","url_abs":"http://arxiv.org/abs/1805.01553v3","url_pdf":"http://arxiv.org/pdf/1805.01553v3.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":"a-reinforcement-learning-approach-to","repo_url":"https://github.com/heidelkin/BIPNMT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"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=1805.01553","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}