{"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/marian-cost-effective-high-quality-neural","title":"Marian: Cost-effective High-Quality Neural Machine Translation in C++","arxiv_id":"1805.12096","date":"2018-05-30","proceeding":"WS 2018 7","authors":["Marcin Junczys-Dowmunt","Kenneth Heafield","Hieu Hoang","Roman Grundkiewicz","Anthony Aue"],"abstract":"This paper describes the submissions of the \"Marian\" team to the WNMT 2018\nshared task. We investigate combinations of teacher-student training,\nlow-precision matrix products, auto-tuning and other methods to optimize the\nTransformer model on GPU and CPU. By further integrating these methods with the\nnew averaging attention networks, a recently introduced faster Transformer\nvariant, we create a number of high-quality, high-performance models on the GPU\nand CPU, dominating the Pareto frontier for this shared task.","url_abs":"http://arxiv.org/abs/1805.12096v1","url_pdf":"http://arxiv.org/pdf/1805.12096v1.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":"marian-cost-effective-high-quality-neural","repo_url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/marian","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.12096","atlas_url":"https://app.syntology.ai/?focus=1805.12096","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}