The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanilla MLM, the virtual tokens, [MASK]s, act as placeholders and gather the contextualized information from unmasked tokens to restore the corrupted information. It raises the question of whether we can append [MASK]s at a later layer, to reduce the sequence length for earlier layers and make the pre-training more efficient. We show: (1) [MASK]s can indeed be appended at a later layer, being disentangled from the word embedding; (2) The gathering of contextualized information from unmasked tokens can be conducted with a few layers. By further increasing the masking rate from 15% to 50%, we can pre-train RoBERTa-base and RoBERTa-large from scratch with only 78% and 68% of the original computational budget without any degradation on the GLUE benchmark. When pre-training with the original budget, our method outperforms RoBERTa for 6 out of 8 GLUE tasks, on average by 0.4%.

Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks. In this paper we propose a new model architecture DeBERTa (Decoding-enhanced BERT with disentangled attention) that improves the BERT and RoBERTa models using two novel techniques. The first is the disentangled attention mechanism, where each word is represented using two vectors that encode its content and position, respectively, and the attention weights among words are computed using disentangled matrices on their contents and relative positions, respectively. Second, an enhanced mask decoder is used to incorporate absolute positions in the decoding layer to predict the masked tokens in model pre-training. In addition, a new virtual adversarial training method is used for fine-tuning to improve models' generalization. We show that these techniques significantly improve the efficiency of model pre-training and the performance of both natural language understand (NLU) and natural langauge generation (NLG) downstream tasks. Compared to RoBERTa-Large, a DeBERTa model trained on half of the training data performs consistently better on a wide range of NLP tasks, achieving improvements on MNLI by +0.9% (90.2% vs. 91.1%), on SQuAD v2.0 by +2.3% (88.4% vs. 90.7%) and RACE by +3.6% (83.2% vs. 86.8%). Notably, we scale up DeBERTa by training a larger version that consists of 48 Transform layers with 1.5 billion parameters. The significant performance boost makes the single DeBERTa model surpass the human performance on the SuperGLUE benchmark (Wang et al., 2019a) for the first time in terms of macro-average score (89.9 versus 89.8), and the ensemble DeBERTa model sits atop the SuperGLUE leaderboard as of January 6, 2021, outperforming the human baseline by a decent margin (90.3 versus 89.8). The pre-trained DeBERTa models and the source code were released at: https://github.com/microsoft/DeBERTa 1 .

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to downstream NLP tasks, they generally require large amounts of compute to be effective. As an alternative, we propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network. Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not. Thorough experiments demonstrate this new pre-training task is more efficient than MLM because the task is defined over all input tokens rather than just the small subset that was masked out. As a result, the contextual representations learned by our approach substantially outperform the ones learned by BERT given the same model size, data, and compute. The gains are particularly strong for small models; for example, we train a model on one GPU for 4 days that outperforms GPT (trained using 30x more compute) on the GLUE natural language understanding benchmark. Our approach also works well at scale, where it performs comparably to RoBERTa and XLNet while using less than 1/4 of their compute and outperforms them when using the same amount of compute.

近年来，基于变压器的预训练模型已获得了很大的进步，成为自然语言处理中最重要的骨干之一。最近的工作表明，变压器内部的注意力机制可能不需要，卷积神经网络和基于多层感知器的模型也已被研究为变压器替代方案。在本文中，我们考虑了一个用于语言模型预训练的图形循环网络，该网络通过本地令牌级通信为每个序列构建一个图形结构，以及与其他代币解耦的句子级表示。原始模型在受监督培训下的特定领域特定文本分类中表现良好，但是，其通过自我监督的方式学习转移知识的潜力尚未得到充分利用。我们通过优化体系结构并验证其在更通用的语言理解任务（英语和中文）中的有效性来填补这一空白。至于模型效率，我们的模型在基于变压器的模型中而不是二次复杂性，而是具有线性复杂性，并且在推断过程中的性能更有效。此外，我们发现与现有基于注意力的模型相比，我们的模型可以生成更多样化的输出，而背景化的功能冗余性较小。

变压器注意机制的二次计算和内存复杂性限制了对长序列建模的可扩展性。在本文中，我们提出了Luna，一种线性统一嵌套关注机制，使Softmax注意力具有两个嵌套线性关注功能，仅产生线性（与二次）的时间和空间复杂度相反。具体地，通过第一注意功能，LUNA将输入序列包装成固定长度的序列。然后，使用第二关注功能未包装包装序列。与更传统的关注机制相比，LUNA引入具有固定长度的附加序列作为输入和额外的相应输出，允许LUNA线性地进行关注操作，同时还存储足够的上下文信息。我们对三个序列建模任务的基准进行了广泛的评估：长上下文序列建模，神经机平移和大型预磨损的屏蔽语言建模。竞争甚至更好的实验结果表明了Luna的有效性和效率与各种各样相比

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned 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 taskspecific 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 score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

在培训数据中拟合复杂的模式，例如推理和争议，是语言预训练的关键挑战。根据最近的研究和我们的经验观察，一种可能的原因是训练数据中的一些易于适应的模式，例如经常共同发生的单词组合，主导和伤害预训练，使模型很难适合更复杂的信息。我们争辩说，错误预测可以帮助找到危害语言理解的这种主导模式。当发生错误预测时，应该经常与导致MIS预测的模型拟合的MIS预测字相同的模式。如果我们可以添加正规化以培训模型，当MIS预测发生并更多地对待更微妙的模式时，可以在更多信息上缩小到这种主导模式时，可以在预训练中有效地安装更多信息。在此动机之后，我们提出了一种新的语言预培训方法，错误预测作为伤害警报（MPA）。在MPA中，当在预训练期间发生错误预测时，我们使用其共同发生信息来指导自我关注模块的多个头部。变压器模块中的一些自我关注头经过优化，以将更低的注意重量分配给频繁地在误报中的输入句子中的单词，同时将更高权重分配给另一个单词。通过这样做，变压器模型训练，以依赖于主导的频繁共同发生模式，而在误报中，当发生错误预测时，在剩余更复杂的信息上更加关注更多。我们的实验表明，MPA加快了伯特和电器的预训练，并提高了他们对下游任务的表现。

本文提出了一种新的预先接受训练的语言模型Debertav3，它通过用更换的令牌检测（RTD）更换掩模语言建模（MLM）来改善原始的Deberta模型，更高的预训练任务。我们的分析表明，Vanilla嵌入了电力中的共享损害培训效率和模型性能。这是因为鉴别器的培训损失和发电机的销售损失在不同的方向上拉动令牌嵌入，从而创造“拔河”动态。因此，我们提出了一种新的梯度 - 解开嵌入共享方法，避免了战争动态，提高了训练效率和预训练模型的质量。我们使用与Deberta相同的设置预先接受了培训的Debertav3，以展示其在广泛的下游自然语言理解（NLU）任务上的特殊表现。以八个任务为例，Debertav3大型模型以八个任务为例，平均得分为91.37％，杜伯塔省的1.37％和电力1.91％，在模型中设置新的最先进（SOTA）具有类似的结构。此外，我们预先培训了多语思伯类Mdeberta，与英语模型相比，对强基线的更大改善。例如，Mdeberta基地达到XNLI的79.8％零射频精度和超过XLM-R基础的3.6％的改进，在此基准上创建了一个新的Sota。我们在HTTPS://github.com/microsoft/deberta公开提供我们预先接受的模型和推理码。

用于预培训语言模型的自我监督学习的核心包括预训练任务设计以及适当的数据增强。语言模型中的大多数数据增强都是独立于上下文的。最近在电子中提出了一个开创性的增强，并通过引入辅助生成网络（发电机）来实现最先进的性能，以产生用于培训主要辨别网络（鉴别者）的上下文化数据增强。然而，这种设计引入了发电机的额外计算成本，并且需要调整发电机和鉴别器之间的相对能力。在本文中，我们提出了一种自增强策略（SAS），其中单个网络用于审视以后的时期的培训常规预训练和上下文化数据增强。基本上，该策略消除了单独的发电机，并使用单个网络共同执行具有MLM（屏蔽语言建模）和RTD（替换令牌检测）头的两个预训练任务。它避免了寻找适当大小的发电机的挑战，这对于在电子中证明的性能至关重要，以及其随后的变体模型至关重要。此外，SAS是一项常规策略，可以与最近或将来的许多新技术无缝地结合，例如杜伯塔省的解除关注机制。我们的实验表明，SAS能够在具有相似或更少的计算成本中优于胶水任务中的电磁和其他最先进的模型。

来自变压器（BERT）的双向编码器表示显示了各种NLP任务的奇妙改进，并且已经提出了其连续的变体来进一步提高预先训练的语言模型的性能。在本文中，我们的目标是首先介绍中国伯特的全文掩蔽（WWM）策略，以及一系列中国预培训的语言模型。然后我们还提出了一种简单但有效的型号，称为Macbert，这在几种方面提高了罗伯塔。特别是，我们提出了一种称为MLM作为校正（MAC）的新掩蔽策略。为了展示这些模型的有效性，我们创建了一系列中国预先培训的语言模型，作为我们的基线，包括BERT，Roberta，Electra，RBT等。我们对十个中国NLP任务进行了广泛的实验，以评估创建的中国人托管语言模型以及提议的麦克白。实验结果表明，Macbert可以在许多NLP任务上实现最先进的表演，我们还通过几种可能有助于未来的研究的调查结果来消融细节。我们开源我们的预先培训的语言模型，以进一步促进我们的研究界。资源可用：https://github.com/ymcui/chinese-bert-wwm

Transfer learning, where a model is first pre-trained on a data-rich task before being finetuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new "Colossal Clean Crawled Corpus", we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.

Recent trends in language modeling have focused on increasing performance through scaling, and have resulted in an environment where training language models is out of reach for most researchers and practitioners. While most in the community are asking how to push the limits of extreme computation, we ask the opposite question: How far can we get with a single GPU in just one day? We investigate the downstream performance achievable with a transformer-based language model trained completely from scratch with masked language modeling for a single day on a single consumer GPU. Aside from re-analyzing nearly all components of the pretraining pipeline for this scenario and providing a modified pipeline with performance close to BERT, we investigate why scaling down is hard, and which modifications actually improve performance in this scenario. We provide evidence that even in this constrained setting, performance closely follows scaling laws observed in large-compute settings. Through the lens of scaling laws, we categorize a range of recent improvements to training and architecture and discuss their merit and practical applicability (or lack thereof) for the limited compute setting.

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by ( 1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Tranformer-based neural machine translation architecture which, despite its simplicity, can be seen as generalizing BERT (due to the bidirectional encoder), GPT (with the left-to-right decoder), and many other more recent pretraining schemes. We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token. BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new stateof-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE. BART also provides a 1.1 BLEU increase over a back-translation system for machine translation, with only target language pretraining. We also report ablation experiments that replicate other pretraining schemes within the BART framework, to better measure which factors most influence end-task performance.

在本文中，我们利用了以前的预训练模型（PTM）的优势，并提出了一种新型的中国预训练的不平衡变压器（CPT）。与以前的中国PTM不同，CPT旨在利用自然语言理解（NLU）和自然语言生成（NLG）之间的共同知识来促进表现。 CPT包括三个部分：共享编码器，一个理解解码器和一代解码器。具有共享编码器的两个特定解码器分别通过蒙版语言建模（MLM）进行了预训练，并分别将自动编码（DAE）任务进行了验证。借助部分共享的体系结构和多任务预培训，CPT可以（1）使用两个解码器学习NLU或NLG任务的特定知识，并且（2）对模型的潜力充分利用了微调。此外，不平衡的变压器节省了计算和存储成本，这使CPT竞争激烈，并极大地加速了文本生成的推断。对各种中国NLU和NLG任务的实验结果显示了CPT的有效性。

在预介质期间，预解压器变压器遭受梯度幅度不匹配：早期层处的梯度远远大于更高层的层。我们所提出的常规程序架构可以减轻这些问题，这为每层增加了三个归一化操作：自我注意后的一层规范，自我注意输出的头部明智的缩放，以及第一完全连接层之后的层标。额外的运营产生忽略不计的计算成本（+ 0.4％的参数增加），但是改善了从12500万到27亿个参数的因果和屏蔽语言模型的预先欣赏困惑和下游任务性能。例如，在我们最强的1.3B参数基线顶部添加NARMFORMER可以在相同的计算预算中更快地达到24％的平等困惑，或者更好地收敛0.27困惑。该模型达到GPT3大（1.3B）零拍摄性能速度快60％。对于屏蔽语言建模，Normformer平均将微调胶水性能提高1.9％。 Fairseq HTTPS://github.com/pytorch/faireq/tree/main/examples/normformer提供培训ormalformer模型的代码。

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary representations to predict the entire content of the masked span, without relying on the individual token representations within it. Span-BERT consistently outperforms BERT and our better-tuned baselines, with substantial gains on span selection tasks such as question answering and coreference resolution. In particular, with the same training data and model size as BERT large , our single model obtains 94.6% and 88.7% F1 on SQuAD 1.1 and 2.0 respectively. We also achieve a new state of the art on the OntoNotes coreference resolution task (79.6% F1), strong performance on the TACRED relation extraction benchmark, and even gains on GLUE. 1 * Equal contribution. 1 Our code and pre-trained models are available at https://github.com/facebookresearch/ SpanBERT.

最近在单语数据和机器翻译（MT）进行微调的预培训方面取得了成功，但尚不清楚如何最好地利用预先训练的模型来完成给定的MT任务。本文在微调MT上的预训练模型时研究了冻结参数的好处和缺点。我们专注于1）微调仅在英语单语言数据的BART上训练的模型。2）微调一个模型，该模型对25种语言的单语言数据进行了培训，Mbart。对于Bart，我们通过冻结大多数模型参数并添加额外的位置嵌入来获得最佳性能。对于MBART，我们将大多数语言对的天真微调的性能与编码器以及大多数解码器搭配。编码器的注意参数对于微调最重要。当将自己限制为越南人对英语的室外训练套装时，我们看到了基线的最大进步。

激活功能可以对降低输入数据的拓扑复杂性产生重大影响，从而提高模型的性能。选择合适的激活函数是神经模型设计中的重要步骤。但是，在基于变压器的语言模型中很少讨论或探索激活功能的选择。事先选择它们的激活功能，然后从预训练中固定到微调。结果，在这个漫长的生命周期中，无法调整它们对模型的电感偏见。此外，随后开发的模型（例如Roberta，Bart和GPT-3）经常跟进先前的工作（例如BERT），以使用相同的激活函数而无需合理。在本文中，我们研究了变压器体系结构中使用理性激活函数（RAF）（RAF）的有效性。与常规，预定义的激活功能相反，RAF可以根据输入数据自适应地学习最佳激活功能。我们的实验表明，基于RAF的变压器（RAFT）比具有GELU函数的香草BERT的验证性更低。我们进一步评估了低和全数据设置中下游任务的筏。我们的结果表明，筏在大多数任务和设置上都优于对应模型。例如，在低数据表情况下（有100个训练示例），木筏在胶水基准上的表现平均高出5.71点，在全数据设置的小队中，平均得分为2.05分。对学到的RAF的形状的分析进一步揭示了它们在预训练模型的不同层之间有很大的变化，并且看起来与常规激活函数大多不同。 RAFT为根据学习的激活功能打开了一个新的研究方向，用于分析和解释预训练的模型。

特定于语言的预训练模型已被证明比单语说在单语法评估设置中更准确，阿拉伯语也不例外。但是，我们发现先前发布的阿拉伯伯特模型显着培训。在这本技术报告中，我们展示了Jaber，Junior Arabic Bert，我们的预用语言模型原型专用于阿拉伯语。我们进行实证研究，以系统地评估模型在各种现有阿拉伯语NLU任务中的性能。实验结果表明，Jaber实现了Alue的最先进的表演，这是阿拉伯语了解评估的新基准，以及成熟的内部基准

Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue and approaches to compression. We then outline directions for future research.