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。

通过多种语言对培训的多语言神经机器翻译（MNMT），由于模型参数的较少和较低的培训成本，通过在多种语言之间共享知识，引起了人们的关注。尽管如此，由于不同翻译方向之间的负面干扰，尤其是在高资源语言上，因此，多语言培训在共享参数中受到语言干扰退化的困扰。在本文中，我们提出了具有高资源语言特定培训（HLT-MT）的多语言翻译模型，以减轻负面干扰，该干扰采用了具有特定于语言的选择机制的两阶段培训。具体而言，我们首先仅使用高资源对训练多语言模型，然后选择解码器顶部的语言特定模块，以增强高资源方向的翻译质量。接下来，对所有可用语料库进行进一步培训，将知识从高资源语言（HRLS）转移到低资源语言（LRLS）。实验结果表明，HLT-MT在WMT-10和Opus-100基准测试上的表现优于各种强基础。此外，分析实验验证了我们方法在减轻多语言训练中负面干扰方面的有效性。

In this paper, we study the use of deep Transformer translation model for the CCMT 2022 Chinese-Thai low-resource machine translation task. We first explore the experiment settings (including the number of BPE merge operations, dropout probability, embedding size, etc.) for the low-resource scenario with the 6-layer Transformer. Considering that increasing the number of layers also increases the regularization on new model parameters (dropout modules are also introduced when using more layers), we adopt the highest performance setting but increase the depth of the Transformer to 24 layers to obtain improved translation quality. Our work obtains the SOTA performance in the Chinese-to-Thai translation in the constrained evaluation.

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。

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.

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。

Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model. Our model, named as GanLM, is trained with two pre-training objectives: replaced token detection and replaced token denoising. Specifically, given masked source sentences, the generator outputs the target distribution and the discriminator predicts whether the target sampled tokens from distribution are incorrect. The target sentence is replaced with misclassified tokens to construct noisy previous context, which is used to generate the gold sentence. In general, both tasks improve the ability of language understanding and generation by selectively using the denoising data. Extensive experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models (PLMs) and achieves state-of-the-art performance.

本报告介绍了在大型多语种计算机翻译中为WMT21共享任务的Microsoft的机器翻译系统。我们参加了所有三种评估轨道，包括大轨道和两个小轨道，前者是无约束的，后两者完全受约束。我们的模型提交到共享任务的初始化用deltalm \脚注{\ url {https://aka.ms/deltalm}}，一个通用的预训练的多语言编码器 - 解码器模型，并相应地使用巨大的收集并行进行微调数据和允许的数据源根据轨道设置，以及应用逐步学习和迭代背翻译方法进一步提高性能。我们的最终提交在自动评估度量方面排名第一的三条轨道。

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）。

Multilingual machine translation suffers from negative interference across languages. A common solution is to relax parameter sharing with language-specific modules like adapters. However, adapters of related languages are unable to transfer information, and their total number of parameters becomes prohibitively expensive as the number of languages grows. In this work, we overcome these drawbacks using hyper-adapters -- hyper-networks that generate adapters from language and layer embeddings. While past work had poor results when scaling hyper-networks, we propose a rescaling fix that significantly improves convergence and enables training larger hyper-networks. We find that hyper-adapters are more parameter efficient than regular adapters, reaching the same performance with up to 12 times less parameters. When using the same number of parameters and FLOPS, our approach consistently outperforms regular adapters. Also, hyper-adapters converge faster than alternative approaches and scale better than regular dense networks. Our analysis shows that hyper-adapters learn to encode language relatedness, enabling positive transfer across languages.

随着自然语言处理领域的最新发展，在使用不同架构的神经机翻译中的使用情况上升了。变压器架构用于实现最先进的准确性，但它们是训练的非常昂贵的昂贵。每个人都不能拥有由高端GPU和其他资源组成的等待。我们在低计算资源上培训我们的模型，并调查结果。正如预期的那样，变形金刚表现出其他架构，但结果有一些令人惊讶的结果。由更多编码器和解码器组成的变形金刚需要花更多的时间来训练，但有更少的BLEU分数。LSTM在实验中表现良好，比较少花时间训练而不是变压器，适合在具有时间限制的情况下使用。

在完全共享所有语言参数的多语言神经机器翻译模型中，通常使用人工语言令牌来指导转换为所需的目标语言。但是，最近的研究表明，预备语言代币有时无法将多语言神经机器翻译模型导航到正确的翻译方向，尤其是在零弹性翻译上。为了减轻此问题，我们提出了两种方法：语言嵌入实施例和语言意识的多头关注，以学习信息丰富的语言表示，以将翻译转换为正确的方向。前者体现了沿着从源到目标的信息流中的不同关键切换点的语言，旨在放大翻译方向引导信号。后者利用矩阵而不是向量来表示连续空间中的语言。矩阵分为多个头，以学习多个子空间中的语言表示。在两个数据集上进行大规模多语言神经机器翻译的实验结果表明，语言意识到的多头注意力受益于监督和零弹性翻译，并大大减轻了脱靶翻译问题。进一步的语言类型学预测实验表明，通过我们的方法学到的基于基质的语言表示能够捕获丰富的语言类型学特征。

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by few other works. We also demonstrate that model pre-training and sparse scaling using Mixture-of-Experts bring large gains to translation performance. The mined data and models are freely available.

在序列到序列学习中，例如，自然语言生成，解码器依赖于注意机制，以有效地从编码器中提取信息。虽然常见的做法是从最后一个编码器层绘制信息，但最近的工作已经提出用于使用来自不同编码器层的表示，以进行多样化的信息。尽管如此，解码器仍然仅获得源序列的单个视图，这可能导致由于层级绕过问题而导致编码器层堆栈的训练不足。在这项工作中，我们提出了层次的多视图解码，其中对于每个解码器层以及来自最后一个编码器层的表示，它作为全局视图，来自其他编码器层的那些是用于立体视图的源序列。系统实验和分析表明，我们成功地解决了层次结构绕过问题，需要几乎可忽略的参数增加，并大大提高了五种不同任务的深度表示的序列到序列学习的性能，即机器翻译，抽象总结，图像标题，视频字幕和医疗报告生成。特别是，我们的方法在八个基准数据集中实现了新的最先进的结果，包括低资源机器转换数据集和两个低资源医疗报告生成数据集。

GPT-2和BERT展示了在各种自然语言处理任务上使用预训练的语言模型（LMS）的有效性。但是，在应用于资源丰富的任务时，LM微调通常会遭受灾难性的遗忘。在这项工作中，我们引入了一个协同的培训框架（CTNMT），该框架是将预训练的LMS集成到神经机器翻译（NMT）的关键。我们提出的CTNMT包括三种技术：a）渐近蒸馏，以确保NMT模型可以保留先前的预训练知识； b）动态的开关门，以避免灾难性忘记预训练的知识； c）根据计划的政策调整学习步伐的策略。我们在机器翻译中的实验表明，WMT14英语 - 德语对的CTNMT获得了最高3个BLEU得分，甚至超过了先前的最先进的预培训辅助NMT NMT的NMT。尽管对于大型WMT14英语法国任务，有400万句话，但我们的基本模型仍然可以显着改善最先进的变压器大型模型，超过1个BLEU得分。代码和模型可以从https://github.com/bytedance/neurst/tree/Master/Master/examples/ctnmt下载。

Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new retrieval-augmented NMT to model contrastively retrieved translation memories that are holistically similar to the source sentence while individually contrastive to each other providing maximal information gains in three phases. First, in TM retrieval phase, we adopt a contrastive retrieval algorithm to avoid redundancy and uninformativeness of similar translation pieces. Second, in memory encoding stage, given a set of TMs we propose a novel Hierarchical Group Attention module to gather both local context of each TM and global context of the whole TM set. Finally, in training phase, a Multi-TM contrastive learning objective is introduced to learn salient feature of each TM with respect to target sentence. Experimental results show that our framework obtains improvements over strong baselines on the benchmark datasets.

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.

Traditional multilingual neural machine translation (MNMT) uses a single model to translate all directions. However, with the increasing scale of language pairs, simply using a single model for massive MNMT brings new challenges: parameter tension and large computations. In this paper, we revisit multi-way structures by assigning an individual branch for each language (group). Despite being a simple architecture, it is challenging to train de-centralized models due to the lack of constraints to align representations from all languages. We propose a localized training recipe to map different branches into a unified space, resulting in an efficient detachable model, Lego-MT. For a fair comparison, we collect data from OPUS and build the first large-scale open-source translation benchmark covering 7 language-centric data, each containing 445 language pairs. Experiments show that Lego-MT (1.2B) brings gains of more than 4 BLEU while outperforming M2M-100 (12B) (We will public all training data, models, and checkpoints)

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。

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。