Attention Is All You Need

GPTKB entity

Statements (50)
Predicate Object
gptkbp:instanceOf gptkb:academic_journal
gptkbp:affiliation gptkb:University_of_Toronto
gptkb:Google_Brain
gptkbp:arXivID 1706.03762
gptkbp:author gptkb:Illia_Polosukhin
gptkb:Łukasz_Kaiser
gptkb:Aidan_N._Gomez
gptkb:Ashish_Vaswani
gptkb:Jakob_Uszkoreit
gptkb:Llion_Jones
gptkb:Niki_Parmar
gptkb:Noam_Shazeer
gptkbp:citation gptkb:BERT:_Pre-training_of_Deep_Bidirectional_Transformers_for_Language_Understanding
gptkb:T5:_Exploring_the_Limits_of_Transfer_Learning_with_a_Unified_Text-to-Text_Transformer
gptkb:GPT:_Improving_Language_Understanding_by_Generative_Pre-Training
over 80,000
gptkbp:contribution self-attention mechanism
improved translation quality
parallelization of training
removal of recurrence in sequence modeling
gptkbp:doi 10.48550/arXiv.1706.03762
gptkbp:field gptkb:machine_learning
natural language processing
gptkbp:focusesOn neural machine translation
gptkbp:hasSection Conclusion
Introduction
Results
Training
Background
References
Model Architecture
https://www.w3.org/2000/01/rdf-schema#label Attention Is All You Need
gptkbp:impact enabled large language models
revolutionized NLP
gptkbp:influenced gptkb:T5
gptkb:BERT
gptkb:GPT
gptkb:XLNet
gptkbp:language English
gptkbp:license arXiv.org perpetual, non-exclusive license
gptkbp:openAccess yes
gptkbp:pages 11
gptkbp:proposedBy Transformer architecture
gptkbp:publicationYear 2017
gptkbp:publishedIn gptkb:Advances_in_Neural_Information_Processing_Systems_(NeurIPS)
gptkbp:trainer gptkb:WMT_2014_English-to-French
gptkb:WMT_2014_English-to-German
gptkbp:url https://arxiv.org/abs/1706.03762
gptkbp:bfsParent gptkb:Large_Language_Models
gptkbp:bfsLayer 5