{"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/neural-sequence-model-training-via-divergence","title":"Neural Sequence Model Training via $α$-divergence Minimization","arxiv_id":"1706.10031","date":"2017-06-30","proceeding":null,"authors":["Sotetsu Koyamada","Yuta Kikuchi","Atsunori Kanemura","Shin-ichi Maeda","Shin Ishii"],"abstract":"We propose a new neural sequence model training method in which the objective\nfunction is defined by $\\alpha$-divergence. We demonstrate that the objective\nfunction generalizes the maximum-likelihood (ML)-based and reinforcement\nlearning (RL)-based objective functions as special cases (i.e., ML corresponds\nto $\\alpha \\to 0$ and RL to $\\alpha \\to1$). We also show that the gradient of\nthe objective function can be considered a mixture of ML- and RL-based\nobjective gradients. The experimental results of a machine translation task\nshow that minimizing the objective function with $\\alpha > 0$ outperforms\n$\\alpha \\to 0$, which corresponds to ML-based methods.","url_abs":"http://arxiv.org/abs/1706.10031v1","url_pdf":"http://arxiv.org/pdf/1706.10031v1.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":"neural-sequence-model-training-via-divergence","repo_url":"https://github.com/sotetsuk/alpha-dimt-icmlws","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"model","task_name":"model"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.10031","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}