%0 Generic %1 devlin2018pretraining %A Devlin, Jacob %A Chang, Ming-Wei %A Lee, Kenton %A Toutanova, Kristina %D 2018 %K thema:Visualbert(Sequential) %T BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding %U http://arxiv.org/abs/1810.04805 %X We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT representations can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE benchmark to 80.4% (7.6% absolute improvement), MultiNLI accuracy to 86.7 (5.6% absolute improvement) and the SQuAD v1.1 question answering Test F1 to 93.2 (1.5% absolute improvement), outperforming human performance by 2.0%.

@conference{devlin2018pretraining, abstract = {We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT representations can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE benchmark to 80.4% (7.6% absolute improvement), MultiNLI accuracy to 86.7 (5.6% absolute improvement) and the SQuAD v1.1 question answering Test F1 to 93.2 (1.5% absolute improvement), outperforming human performance by 2.0%.}, added-at = {2021-06-05T13:24:00.000+0200}, author = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, biburl = {https://www.bibsonomy.org/bibtex/267d62a65a763fd69ac4cc1fc0ca990e9/jan_seidlein}, description = {[1810.04805] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding}, interhash = {a74f4c3853d3f0340e75546639134e91}, intrahash = {67d62a65a763fd69ac4cc1fc0ca990e9}, keywords = {thema:Visualbert(Sequential)}, note = {cite arxiv:1810.04805Comment: 13 pages}, timestamp = {2021-06-05T13:24:00.000+0200}, title = {BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding}, url = {http://arxiv.org/abs/1810.04805}, year = 2018 }