{"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/efficient-machine-translation-with-model","title":"Efficient Machine Translation with Model Pruning and Quantization","arxiv_id":null,"date":"2021-11-01","proceeding":"WMT (EMNLP) 2021 11","authors":["Maximiliana Behnke","Nikolay Bogoychev","Alham Fikri Aji","Kenneth Heafield","Graeme Nail","Qianqian Zhu","Svetlana Tchistiakova","Jelmer Van der Linde","Pinzhen Chen","Sidharth Kashyap","Roman Grundkiewicz"],"abstract":"We participated in all tracks of the WMT 2021 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions. Our submissions combine several efficiency strategies: knowledge distillation, a simpler simple recurrent unit (SSRU) decoder with one or two layers, lexical shortlists, smaller numerical formats, and pruning. For the CPU track, we used quantized 8-bit models. For the GPU track, we experimented with FP16 and 8-bit integers in tensorcores. Some of our submissions optimize for size via 4-bit log quantization and omitting a lexical shortlist. We have extended pruning to more parts of the network, emphasizing component- and block-level pruning that actually improves speed unlike coefficient-wise pruning.","url_abs":"https://aclanthology.org/2021.wmt-1.74","url_pdf":"https://aclanthology.org/2021.wmt-1.74.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":"efficient-machine-translation-with-model","repo_url":"https://github.com/marian-nmt/marian","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}