[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-140254-105":59,"doc-detail-140254-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","attention-is-all-you-need","Attention Is All You Need","","Dominant sequence transduction approaches rely on encoder-decoder designs built from recurrent or convolutional neural networks, typically connecting them with an attention mechanism. This paper introduces the Transformer: a simplified architecture that uses attention mechanisms only, eliminating recurrence and convolutions. Experiments on two machine translation tasks show higher quality, stronger parallelization, and substantially faster training. Results reach 28.4 BLEU on WMT 2014 English-to-German and a new single-model state of the art of 41.0 BLEU on English-to-French.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/attention-is-all-you-need/140254/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/attention-is-all-you-need/140254.png","ImageObject",300,407,{"name":92,"@type":93},"วิน","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-16","2026-08-24",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the Transformer address compared with recurrent and convolutional models?","Question",{"text":112,"@type":113},"The Transformer targets the inherently sequential computation of recurrent models, enabling significantly more parallelization while capturing global dependencies through attention.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the Transformer architecture differ from traditional encoder-decoder networks?",{"text":117,"@type":113},"It removes recurrence and convolutions entirely, relying solely on attention mechanisms to connect input and output representations.",{"name":119,"@type":110,"acceptedAnswer":120},"What translation performance results are reported on WMT 2014 tasks?",{"text":121,"@type":113},"The model achieves 28.4 BLEU on English-to-German and 41.0 BLEU on English-to-French, establishing a new single-model state of the art on the latter.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},140254,1787571343,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},2336475104736,"https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222","Attention Is All You Need  \nAshish Vaswani􀀃  \nGoogle Brain [avaswani@google.com](avaswani@google.com)  \nLlion Jones􀀃  \nGoogle Research [llion@google.com](llion@google.com)  \nNoam Shazeer􀀃  \nGoogle Brain [noam@google.com](noam@google.com)  \nNiki Parmar􀀃  \nGoogle Research [nikip@google.com](nikip@google.com)  \nJakob Uszkoreit􀀃 Google Research [usz@google.com](usz@google.com)  \nAidan N. Gomez􀀃 y  \nUniversity of Toronto [aidan@cs.toronto.edu](aidan@cs.toronto.edu)  \nŁukasz Kaiser􀀃  \nGoogle Brain [lukaszkaiser@google.com](lukaszkaiser@google.com)  \nIllia Polosukhin􀀃 z  \n[illia.polosukhin@gmail.com](illia.polosukhin@gmail.com)  \nAbstract  \nThe dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models tobe superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 Englishto-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.0 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature.  \n1 Introduction  \nRecurrent neural networks, long short-term memory [12] and gated recurrent [7] neural networks in particular, have been firmly established as state of the art approaches in sequence modeling and transduction problems such as language modeling and machine translation [29, 2, 5] . Numerous efforts have since continued to push the boundaries of recurrent language models and encoder-decoder architectures [31, 21, 13] .  \n􀀃 Equal contribution. Listing order is random. Jakob proposed replacing RNNs with self-attention and started the effort to evaluate this idea. Ashish, with Illia, designed and implemented the first Transformer models and has been crucially involved in every aspect of this work. Noam proposed scaled dot-product attention, multi-head attention and the parameter-free position representation and became the other person involved in nearly every detail. Niki designed, implemented, tuned and evaluated countless model variants in our original codebase and tensor2tensor. Llion also experimented with novel model variants, was responsible for our initial codebase, andefficient inference and visualizations. Lukasz and Aidan spent countless long days designing various parts of and implementing tensor2tensor, replacing our earlier codebase, greatly improving results and massively accelerating our research.  \nyWork performed while at Google Brain.  \nzWork performed while at Google Research.  \n31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.  \nRecurrent models typically factor computation along the symbol positions of the input and output sequences. Aligning the positions to steps in computation time, they generate a sequence of hidden states ht , as a function of the previous hidden state ht􀀀1 and the input for position t. This inherently sequential nature precludes parallelization within training examples, which becomes critical at longer sequence lengths, as memory constraints limit batching across examples. Recent work has achieved significant improvements in computational efficiency through factorization tricks [18] and conditional computation [26], while also improving model performance in case of the latter. The fundamental constraint of sequential computation, however, remains.  \nAttention mechanisms have become an integral part of compelling sequence modeling and transduction models","cbCaia2cR38k3uXF","https://ap.wps.com/l/cbCaia2cR38k3uXF","pdf",569417,11,"English","# Abstract\n# Introduction\n# Background\n## Self-attention\n## Related architectures","[{\"question\":\"What problem does the Transformer address compared with recurrent and convolutional models?\",\"answer\":\"The Transformer targets the inherently sequential computation of recurrent models, enabling significantly more parallelization while capturing global dependencies through attention.\"},{\"question\":\"How does the Transformer architecture differ from traditional encoder-decoder networks?\",\"answer\":\"It removes recurrence and convolutions entirely, relying solely on attention mechanisms to connect input and output representations.\"},{\"question\":\"What translation performance results are reported on WMT 2014 tasks?\",\"answer\":\"The model achieves 28.4 BLEU on English-to-German and 41.0 BLEU on English-to-French, establishing a new single-model state of the art on the latter.\"}]","Attention Is All You Need | PDF",28]