已显示自动回归神经序列模型在文本生成任务中有效。然而，它们的左右解码顺序可防止产生并行化。插入变压器（Stern等，2019）是一种有吸引力的替代方案，允许在单一代币上输出多个令牌。然而，由于绝对位置编码和基于插入的生成方案的不兼容，需要刷新每个步骤的所生成的部分假设中的每个令牌的编码，这可能是昂贵的。我们设计一种用于分数位置编码（FPE）的插入变压器的新型增量位置编码方案，其允许重用在先前步骤中计算的表示。关于各种语言生成任务的实证研究证明了FPE的有效性，这导致批量解码减少浮点操作和潜伏期改善。

自回归（AR）和非自动增加（NAR）模型对性能和延迟具有自己的优势，将它们与一个模型相结合，可能会利用两者。目前的组合框架更多地关注多个解码范例的集成，具有统一的生成模型，例如，屏蔽语言模型。然而，由于训练目标和推理之间的差距，概括可能对性能有害。在本文中，我们的目标是通过在统一框架下保留AR和NAR的原始目标来缩小差距。具体地，我们通过将AR和NAR共同建模（左右，左右和直）与新引入的方向变量来提出定向变压器（Diformer），这通过控制每个的预测令牌在那方面有特定的依赖关系。通过方向实现的统一成功地保留了AR和NAR中使用的原始依赖性假设，保留了泛化和性能。 4 WMT基准测试的实验表明，Diformer优于当前的联合建模工作，适用于AR和NAR解码的1.5个以上的BLEU积分，也对最先进的独立AR和NAR模型具有竞争力。

非自动回旋（NAR）模型的计算能力比自回归模型较少，但牺牲生成质量可以生成句子。先前的研究通过迭代解码解决了这个问题。这项研究建议将最近的邻居用作NAR解码器的初始状态，并迭代编辑。我们提出了一种新颖的培训策略，以了解有关邻居的编辑操作，以改善NAR文本生成。实验结果表明，所提出的方法（邻域）在JRC-ACQUISIE EN-DE DATASET上获得了更高的翻译质量（比香草变压器高1.69点（比香草变压器高1.69点），而解码迭代率较少（少于十分之一）使用最近的邻居翻译。我们还确认了所提出的方法对数据到文本任务（Wikibio）的有效性。此外，所提出的方法在WMT'14 EN-DE数据集上优于NAR基线。我们还报告了建议方法中使用的邻居示例的分析。

无向神经序列模型实现了与最先进的定向序列模型竞争的性能，这些序列模型在机器翻译任务中从左到右单调。在这项工作中，我们培训一项政策，该政策是通过加强学习来学习预先训练的，无向翻译模型的发电顺序。我们表明，通过我们学习的订单解码的翻译可以实现比从左到右解码的输出量更高的BLEU分数或由来自Mansimov等人的学习顺序解码的输出。 （2019）关于WMT'14德语翻译任务。从De-Zh，WMT'16英语 - 罗马尼亚语和WMT'21英语翻译任务的最大来源和目标长度为30的示例，我们的学习订单优于六个任务中的四个启发式生成订单。我们接下来通过定性和定量分析仔细分析学习的订单模式。我们表明我们的政策通常遵循外部到内部顺序，首先预测最左右的位置，然后向中间移动，同时在开始时跳过不太重要的单词。此外，该政策通常在连续步骤中预测单个语法构成结构的位置。我们相信我们的调查结果可以对无向生成模型的机制提供更多的见解，并鼓励在这方面进一步研究。我们的代码在HTTPS://github.com/jiangyctarheel/undirectect - generation

最近的神经机翻译研究探索了灵活的发行订单，作为左右一代的替代品。然而，培训非单调模型带来了新的并发症：如何在同一最终结果到达的订单组合爆炸时搜索良好的订单？此外，这些自动排序如何与人类翻译的实际行为进行比较？目前的模型依靠手动构建的偏见或留下自己的所有可能性。在本文中，我们分析了人工后编辑所产生的排序，并使用它们培训自动编辑后系统。我们将生成的系统与由左右和随机编辑排序训练的人进行比较。我们观察到人类倾向于遵循几乎左右的顺序，而是有趣的偏差，例如首选通过纠正标点符号或动词而开始。

与单案摘要相比，抽象性多文件摘要（MDS）对其冗长和链接的来源的表示和覆盖范围提出了挑战。这项研究开发了一个平行的层次变压器（PHT），具有MDS的注意对齐。通过合并单词和段落级的多头注意，PHT的层次结构可以更好地处理令牌和文档级别的依赖项。为了指导解码到更好的源文档覆盖范围，然后将注意力调整机制引入以校准光束搜索，并预测的最佳注意力分布。根据Wikisum数据，进行了全面的评估，以测试拟议的体系结构对MD的改进。通过更好地处理内部和跨文档的信息，结果胭脂和人类评估都表明，我们的分层模型以相对较低的计算成本生成较高质量的摘要。

It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a sentence sequentially and equally. In this paper, we propose an uncertainty-aware image captioning framework, which parallelly and iteratively operates insertion of discontinuous candidate words between existing words from easy to difficult until converged. We hypothesize that high-uncertainty words in a sentence need more prior information to make a correct decision and should be produced at a later stage. The resulting non-autoregressive hierarchy makes the caption generation explainable and intuitive. Specifically, we utilize an image-conditioned bag-of-word model to measure the word uncertainty and apply a dynamic programming algorithm to construct the training pairs. During inference, we devise an uncertainty-adaptive parallel beam search technique that yields an empirically logarithmic time complexity. Extensive experiments on the MS COCO benchmark reveal that our approach outperforms the strong baseline and related methods on both captioning quality as well as decoding speed.

Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence assumption on target sequences, falling short of characterizing human language data. This drawback results in less informative learning signals for NAR models under conventional MLE training, thereby yielding unsatisfactory accuracy compared to their autoregressive (AR) counterparts. In this paper, we propose a simple and model-agnostic multi-task learning framework to provide more informative learning signals. During training stage, we introduce a set of sufficiently weak AR decoders that solely rely on the information provided by NAR decoder to make prediction, forcing the NAR decoder to become stronger or else it will be unable to support its weak AR partners. Experiments on WMT and IWSLT datasets show that our approach can consistently improve accuracy of multiple NAR baselines without adding any additional decoding overhead.

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR outputs. Previous works usually use a sequence-to-sequence model to correct an ASR output sentence autoregressively, which causes large latency and cannot be deployed in online ASR services. A straightforward solution to reduce latency, inspired by non-autoregressive (NAR) neural machine translation, is to use an NAR sequence generation model for ASR error correction, which, however, comes at the cost of significantly increased ASR error rate. In this paper, observing distinctive error patterns and correction operations (i.e., insertion, deletion, and substitution) in ASR, we propose FastCorrect, a novel NAR error correction model based on edit alignment. In training, FastCorrect aligns each source token from an ASR output sentence to the target tokens from the corresponding ground-truth sentence based on the edit distance between the source and target sentences, and extracts the number of target tokens corresponding to each source token during edition/correction, which is then used to train a length predictor and to adjust the source tokens to match the length of the target sentence for parallel generation. In inference, the token number predicted by the length predictor is used to adjust the source tokens for target sequence generation. Experiments on the public AISHELL-1 dataset and an internal industrial-scale ASR dataset show the effectiveness of FastCorrect for ASR error correction: 1) it speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model; and 2) it outperforms the popular NAR models adopted in neural machine translation and text edition by a large margin.

在几乎所有文本生成应用中，Word序列在左右（L2R）或左右（R2L）方式中构造，因为自然语言句子是写入L2R或R2L。但是，我们发现自然语言书面订单对文本生成至关重要。在本文中，我们提出了一种螺旋语言建模（SLM），这是一种普遍的方法，使人们能够构建超出L2R和R2L订单的自然语言句子。 SLM允许其中一个从结果文本内的任意令牌开始，并在所选的任意令牌中展开REST令牌。它使解码顺序除了语言模型困惑之外的新优化目标，这进一步提高了所生成文本的分集和质量。此外，SLM使得可以通过选择正确的开始令牌来操纵文本构建过程。 SLM还将生成排序引入了额外的正则化，以提高低资源方案中的模型稳健性。 8次广泛研究的神经机翻译（NMT）任务的实验表明，与传统的L2R解码方法相比，SLM高达4.7 BLEU增加。

我们为神经机翻译（NMT）提供了一个开源工具包。新工具包主要基于拱形变压器（Vaswani等，2017）以及下面详述的许多其他改进，以便创建一个独立的，易于使用，一致和全面的各个领域的机器翻译任务框架。它是为了支持双语和多语言翻译任务的工具，从构建各个语料库的模型开始推断新的预测或将模型打包给提供功能的JIT格式。

We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.

Diffusion models have achieved state-of-the-art synthesis quality on visual and audio tasks, and recent works adapt them to textual data by diffusing on the embedding space. But the difference between the continuous data space and the embedding space raises challenges to the diffusion model, which have not been carefully explored. In this paper, we conduct systematic studies and analyze the challenges threefold. Firstly, the data distribution is learnable for embeddings, which may lead to the collapse of the loss function. Secondly, as the norm of embedding varies between popular and rare words, adding the same noise scale will lead to sub-optimal results. In addition, we find that noises sampled from a standard Gaussian distribution may distract the diffusion process. To solve the above challenges, we propose Difformer, a denoising diffusion probabilistic model based on Transformer, which consists of three techniques including utilizing an anchor loss function, a layer normalization module for embeddings, and a norm factor to the Gaussian noise. All techniques are complementary to each other and critical to boosting the model performance together. Experiments are conducted on benchmark datasets over two seminal text generation tasks including machine translation and text summarization. The results show that Difformer significantly outperforms the embedding diffusion baselines, while achieving competitive results with strong autoregressive baselines.

变压器架构已成功用于学习源代码表示。图形表示像抽象语法树（AST）和源代码序列之间的融合使得使用电流接近计算地难以用于大输入序列长度。源代码可以有需要更大序列长度的远程依赖性，以有效地模拟模型。电流方法在序列长度方面具有计算和内存成本的二次生长。在实际情况下使用这些模型很难。在这项工作中，我们通过使用图形邻接矩阵作为稀疏自我关注机制的注意掩模以及使用图形扩散机制来模拟更长范围令牌依赖性的关注掩模来提出源代码片段的调节。我们的型号在Bleu，Meteor和Rouge-L指标中达到最先进的结果，用于代码摘要任务以及可变误用任务的最先进的准确性。与先前作品的二次生长相比，我们模型的内存使用和推理时间具有相对于输入序列长度的线性生长。

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.

Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese <-> English), and the results show that the proposed method achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.

Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better models. Recent works have shown character-level models to be competitive with subword models, but costly in terms of time and computation. Character-level models with a downsampling component alleviate this, but at the cost of quality, particularly for machine translation. This work analyzes the problems of previous downsampling methods and introduces a novel downsampling method which is informed by subwords. This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.

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。

Modern multi-document summarization (MDS) methods are based on transformer architectures. They generate state of the art summaries, but lack explainability. We focus on graph-based transformer models for MDS as they gained recent popularity. We aim to improve the explainability of the graph-based MDS by analyzing their attention weights. In a graph-based MDS such as GraphSum, vertices represent the textual units, while the edges form some similarity graph over the units. We compare GraphSum's performance utilizing different textual units, i. e., sentences versus paragraphs, on two news benchmark datasets, namely WikiSum and MultiNews. Our experiments show that paragraph-level representations provide the best summarization performance. Thus, we subsequently focus oAnalysisn analyzing the paragraph-level attention weights of GraphSum's multi-heads and decoding layers in order to improve the explainability of a transformer-based MDS model. As a reference metric, we calculate the ROUGE scores between the input paragraphs and each sentence in the generated summary, which indicate source origin information via text similarity. We observe a high correlation between the attention weights and this reference metric, especially on the the later decoding layers of the transformer architecture. Finally, we investigate if the generated summaries follow a pattern of positional bias by extracting which paragraph provided the most information for each generated summary. Our results show that there is a high correlation between the position in the summary and the source origin.

This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every $k$ tokens, $k>1$) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade off the translation quality and speed by adjusting $k$. In addition, by integrating other modeling techniques (e.g., sequence-level knowledge distillation and deep-encoder-shallow-decoder layer allocation strategy) and a mass of engineering efforts, HRT improves 80\% inference speed and achieves equivalent translation performance with the same-capacity AT counterpart. Our fastest system reaches 6k+ words/second on the GPU latency setting, estimated to be about 3.1x faster than the last year's winner.