已被证明在改善神经电机翻译（NMT）系统方面有效的深度编码器，但是当编码器层数超过18时，它达到了翻译质量的上限。更糟糕的是，更深的网络消耗了很多内存，使其无法实现有效地训练。在本文中，我们呈现了共生网络，其包括完整的网络作为共生主网络（M-Net）和另一个具有相同结构的共享子网，但层数较少为共生子网（S-Net）。我们在变压器深度（M-N）架构上采用共生网络，并在NMT中定义M-Net和S-Net之间的特定正则化损耗$ \ mathcal {l} _ {\ tau} $。我们对共生网络进行联合培训，并旨在提高M净性能。我们拟议的培训策略在CMT'14 en-> De，De-> EN和EN-> FR任务的经典培训下将变压器深（12-6）改善了0.61,0.49和0.69 BLEU。此外，我们的变压器深（12-6）甚至优于经典变压器深度（18-6）。

变压器结构由一系列编码器和解码器网络层堆叠，在神经机器翻译中实现了重大发展。但是，假设下层提供了微不足道或冗余的信息，那么香草变压器主要利用顶层表示形式，从而忽略了潜在有价值的底层特征。在这项工作中，我们提出了组转换器模型（GTRAN），该模型将编码器和解码器的多层表示分为不同的组，然后融合这些组特征以生成目标词。为了证实所提出方法的有效性，对三个双语翻译基准和两个多语言翻译任务进行了广泛的实验和分析实验，包括IWLST-14，IWLST-17，IWLST-17，LDC，WMT-14和OPUS-100基准。实验和分析结果表明，我们的模型通过一致的增益优于其变压器对应物。此外，它可以成功扩展到60个编码层和36个解码器层。

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyperparameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.

The 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 to be 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. * 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, and efficient 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.† Work performed while at Google Brain.‡ Work performed while at Google Research.

In this paper, we propose a novel architecture, the Enhanced Interactive Transformer (EIT), to address the issue of head degradation in self-attention mechanisms. Our approach replaces the traditional multi-head self-attention mechanism with the Enhanced Multi-Head Attention (EMHA) mechanism, which relaxes the one-to-one mapping constraint among queries and keys, allowing each query to attend to multiple keys. Furthermore, we introduce two interaction models, Inner-Subspace Interaction and Cross-Subspace Interaction, to fully utilize the many-to-many mapping capabilities of EMHA. Extensive experiments on a wide range of tasks (e.g. machine translation, abstractive summarization, grammar correction, language modelling and brain disease automatic diagnosis) show its superiority with a very modest increase in model size.

多尺度特征层次结构已在计算机视觉区域的成功中得到了见证。这进一步激发了研究人员设计自然语言处理的多尺度变压器，主要是基于自我发项机制。例如，限制跨头部的接收场或通过卷积提取局部细粒度特征。但是，大多数现有作品都直接建模了本地功能，但忽略了单词边界信息。这导致了缺乏解释性的多余和模棱两可的注意力分布。在这项工作中，我们在不同的语言单元中定义了这些量表，包括子字，单词和短语。我们通过基于单词边界信息和短语级别的先验知识之间建立量表之间的关系来构建多尺度变压器模型。提出的\ textbf {u} niversal \ textbf {m} ulti \ textbf {s} cale \ textbf {t} ransformer，即在两个序列生成任务上评估。值得注意的是，它在几个测试组上的强大基线上产生了一致的性能，而无需牺牲效率。

Relying entirely on an attention mechanism, the Transformer introduced by Vaswani et al. ( 2017) achieves state-of-the-art results for machine translation. In contrast to recurrent and convolutional neural networks, it does not explicitly model relative or absolute position information in its structure. Instead, it requires adding representations of absolute positions to its inputs. In this work we present an alternative approach, extending the self-attention mechanism to efficiently consider representations of the relative positions, or distances between sequence elements. On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1.3 BLEU and 0.3 BLEU over absolute position representations, respectively. Notably, we observe that combining relative and absolute position representations yields no further improvement in translation quality. We describe an efficient implementation of our method and cast it as an instance of relation-aware self-attention mechanisms that can generalize to arbitrary graphlabeled inputs.

Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance of the model and analyze the roles played by them. We find that the most important and confident heads play consistent and often linguistically-interpretable roles. When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L 0 penalty, we observe that specialized heads are last to be pruned. Our novel pruning method removes the vast majority of heads without seriously affecting performance. For example, on the English-Russian WMT dataset, pruning 38 out of 48 encoder heads results in a drop of only 0.15 BLEU. 1

端到端（E2E）语音到文本翻译（ST）通常取决于通过语音识别或文本翻译任务使用源成绩单预处理其编码器和/或解码器，否则翻译性能会大大下降。但是，笔录并不总是可用的，在文献中很少研究这种预处理的E2E ST。在本文中，我们重新审视了这个问题，并探讨了仅在语音翻译对培训的E2E ST质量的程度。我们重新审查了几种证明对ST的有益的技术，并提供了一系列最佳实践，这些实践使基于变压器的E2E ST系统偏向于从头开始训练。此外，我们提出了参数化的距离惩罚，以促进语音自我注意模型中的位置建模。在涵盖23种语言的四个基准测试中，我们的实验表明，在不使用任何成绩单或预处理的情况下，提议的系统达到甚至优于先前采用预处理的研究，尽管差距仍然存在（极为）低资源的设置。最后，我们讨论了神经声学特征建模，其中神经模型旨在直接从原始语音信号中提取声学特征，以简化电感偏见并为模型描述语音增添自由度。我们第一次证明了它的可行性，并在ST任务上表现出令人鼓舞的结果。

Directly training a document-to-document (Doc2Doc) neural machine translation (NMT) via Transformer from scratch, especially on small datasets usually fails to converge. Our dedicated probing tasks show that 1) both the absolute position and relative position information gets gradually weakened or even vanished once it reaches the upper encoder layers, and 2) the vanishing of absolute position information in encoder output causes the training failure of Doc2Doc NMT. To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention. Specifically, we integrate absolute positional information, i.e., position embeddings, into the query-key pairs both in self-attention and cross-attention through a simple yet effective addition operation. Moreover, we also integrate relative position encoding in self-attention. The proposed P-Transformer utilizes sinusoidal position encoding and does not require any task-specified position embedding, segment embedding, or attention mechanism. Through the above methods, we build a Doc2Doc NMT model with P-Transformer, which ingests the source document and completely generates the target document in a sequence-to-sequence (seq2seq) way. In addition, P-Transformer can be applied to seq2seq-based document-to-sentence (Doc2Sent) and sentence-to-sentence (Sent2Sent) translation. Extensive experimental results of Doc2Doc NMT show that P-Transformer significantly outperforms strong baselines on widely-used 9 document-level datasets in 7 language pairs, covering small-, middle-, and large-scales, and achieves a new state-of-the-art. Experimentation on discourse phenomena shows that our Doc2Doc NMT models improve the translation quality in both BLEU and discourse coherence. We make our code available on Github.

机器翻译历史上的重要突破之一是变压器模型的发展。不仅对于各种翻译任务，而且对于大多数其他NLP任务都是革命性的。在本文中，我们针对一个基于变压器的系统，该系统能够将德语用源句子转换为其英语的对应目标句子。我们对WMT'13数据集的新闻评论德语 - 英语并行句子进行实验。此外，我们研究了来自IWSLT'16数据集的培训中包含其他通用域数据以改善变压器模型性能的效果。我们发现，在培训中包括IWSLT'16数据集，有助于在WMT'13数据集的测试集中获得2个BLEU得分点。引入定性分析以分析通用域数据的使用如何有助于提高产生的翻译句子的质量。

以前的工作主要侧重于改善NLU任务的交叉传输，具有多语言预用编码器（MPE），或提高与伯特的监督机器翻译的性能。然而，探索了，MPE是否可以有助于促进NMT模型的交叉传递性。在本文中，我们专注于NMT中的零射频转移任务。在此任务中，NMT模型培训，只有一个语言对的并行数据集和搁置架MPE，然后它直接测试在零拍语言对上。我们为此任务提出了Sixt，一个简单而有效的模型。 SIXT利用了两阶段培训计划利用MPE，并进一步改进了解离编码器和容量增强的解码器。使用此方法，SIMPT显着优于MBart，这是一个用于NMT的预磨削的多语言编码器解码器模型，平均改善了14个源语言的零拍摄的任何英语测试集上的7.1 BLEU。此外，培训计算成本和培训数据较少，我们的模型在15个任何英语测试组上实现了比Criss和M2M-100，两个强大的多语言NMT基线更好的性能。

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference -sometimes prohibitively so in the case of very large data sets and large models. Several authors have also charged that NMT systems lack robustness, particularly when input sentences contain rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using residual connections as well as attention connections from the decoder network to the encoder. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. To directly optimize the translation BLEU scores, we consider refining the models by using reinforcement learning, but we found that the improvement in the BLEU scores did not reflect in the human evaluation. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system.

由于其二次复杂性，是变压器中的关注模块，其是变压器中的重要组件不能高效地扩展到长序列。许多工作侧重于近似于尺寸的圆点 - 指数的软MAX功能，导致分二次甚至线性复杂性变压器架构。但是，我们表明这些方法不能应用于超出点的指数样式的更强大的注意模块，例如，具有相对位置编码（RPE）的变压器。由于在许多最先进的模型中，相对位置编码被用作默认，设计可以包含RPE的高效变压器是吸引人的。在本文中，我们提出了一种新颖的方法来加速对RPE的转化仪的关注计算在核心化的关注之上。基于观察到相对位置编码形成Toeplitz矩阵，我们数在数学上表明，可以使用快速傅里叶变换（FFT）有效地计算具有RPE的核化注意。使用FFT，我们的方法实现$ \ mathcal {o}（n \ log n）$时间复杂性。有趣的是，我们进一步证明使用相对位置编码适当地可以减轻香草群关注的培训不稳定问题。在广泛的任务上，我们经验证明我们的模型可以从头开始培训，没有任何优化问题。学习模型比许多高效的变压器变体更好地执行，并且在长序列制度中比标准变压器更快。

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

多语种NMT已成为MT在生产中部署的有吸引力的解决方案。但是要匹配双语质量，它符合较大且较慢的型号。在这项工作中，我们考虑了几种方法在推理时更快地使多语言NMT变得更快而不会降低其质量。我们在两种20语言多平行设置中尝试几个“光解码器”架构：在TED会谈中小规模和帕拉克曲线上的大规模。我们的实验表明，将具有词汇过滤的浅解码器组合在于，在翻译质量下没有损失的速度超过两倍。我们用Bleu和Chrf（380语言对），鲁棒性评估和人类评估验证了我们的研究结果。

我们介绍了双图：一种简单但有效的训练策略，以提高神经机器翻译（NMT）性能。它由两个程序组成：双向预处理和单向填充。这两个过程均使用SIMCUT，这是一种简单的正则化方法，迫使原始句子对的输出分布之间的一致性。在不利用额外的数据集通过反翻译或集成大规模预认证的模型的情况下，BI-Simcut可以在五个翻译基准（数据尺寸从160K到20.20万）中实现强大的翻译性能：EN-的BLEU得分为31.16，EN-> DE和38.37的BLEU得分为38.37 de-> en在IWSLT14数据集上，en-> de的30.78和35.15在WMT14数据集上进行DE-> en，而WMT17数据集中的ZH-> EN为27.17。 Simcut不是一种新方法，而是简化和适用于NMT的cutoff（Shen等，2020）的版本，可以将其视为基于扰动的方法。鉴于Simcut和Bi-Simcut的普遍性和简单性，我们认为它们可以作为未来NMT研究的强大基准。

变压器注意机制中的设计选择，包括弱电感偏置和二次计算复杂性，限制了其用于建模长序列的应用。在本文中，我们介绍了一个简单的，理论上的，单头的门控注意机制，配备了（指数）移动平均线，以将局部依赖性的电感偏置纳入位置 - 敏锐的注意机制中。我们进一步提出了一个具有线性时间和空间复杂性的大型变体，但通过将整个序列分为固定长度的多个块，仅产生最小的质量损失。对广泛的序列建模基准测试的广泛实验，包括远距离竞技场，神经机器翻译，自动回归语言建模以及图像和语音分类，表明，巨人比其他序列模型取得了重大改进，包括变种物的变体和最新的变体模型状态空间模型。

多语种神经机翻译（MNMT）旨在通过单一模型进行翻译多种语言，并且由于具有共享参数的不同语言的有效知识传输，已被证明是成功的。但是，它仍然是一个开放的问题，应该共享哪些参数，并且需要是特定于任务的。目前，常识是启发式设计或搜索特定语言的模块，这很难找到最佳配置。在本文中，我们提出了一种基于新的参数差异化方法，允许模型确定在训练期间应该是哪个参数。灵感来自蜂窝分化，我们方法中的每个共享参数都可以动态区分为更专业化的类型。我们还将差分标准定义为任务间梯度相似性。因此，突出的任务渐变间的参数更可能是特定于语言的。关于多语言数据集的大量实验表明，我们的方法显着优于不同参数共享配置的各种强基线。进一步的分析表明，通过我们的方法获得的参数共享配置与语言近似度很好地相关。

由于其误差传播，延迟较少和更少的参数较少的潜力，端到端语音到文本翻译〜（e2e-st）变得越来越受欢迎。鉴于三联培训语料库$ \ langle演讲，转录，翻译\ rangle $，传统的高质量E2E-ST系统利用$ \ langle演讲，转录\ rangle $配对预先培训模型，然后利用$ \ Langle演讲，翻译\ rangle $配对进一步优化它。然而，该过程仅涉及每个阶段的两个元组数据，并且该松散耦合不能完全利用三重态数据之间的关联。在本文中，我们试图基于语音输入模拟转录和翻译的联合概率，以直接利用这种三重态数据。基于此，我们提出了一种新的正规化方法，用于改进三重态数据中双路分解协议的模型培训，理论上应该是相等的。为实现这一目标，我们将两个Kullback-Leibler发散正规化术语介绍到模型培训目的中，以减少双路径输出概率之间的不匹配。然后，训练有素的模型可以通过预定义的早期停止标签自然地被视为E2E-ST模型。 Must-C基准测试的实验表明，我们所提出的方法在所有8个语言对上显着优于最先进的E2E-ST基线，同时在自动语音识别任务中实现更好的性能。我们的代码在https://github.com/duyichao/e2e -st-tda开放。