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。

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

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。

我们引入了翻译误差校正（TEC），这是自动校正人类生成的翻译的任务。机器翻译（MT）的瑕疵具有长期的动机系统，可以通过自动编辑后改善变化后的转换。相比之下，尽管人类直觉上犯了不同的错误，但很少有人注意自动纠正人类翻译的问题，从错别字到翻译约定的矛盾之处。为了调查这一点，我们使用三个TEC数据集构建和释放ACED语料库。我们表明，与自动后编辑数据集中的MT错误相比，TEC中的人类错误表现出更加多样化的错误，翻译流利性误差要少得多，这表明需要专门用于纠正人类错误的专用TEC模型。我们表明，基于人类错误的合成错误的预训练可将TEC F-SCORE提高多达5.1点。我们通过九名专业翻译编辑进行了人类的用户研究，发现我们的TEC系统的帮助使他们产生了更高质量的修订翻译。

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。

自动编辑（APE）旨在通过自动纠正机器翻译输出中的错误来减少手动后编辑工作。由于人类注销的培训数据数量有限，数据稀缺是所有猿类系统所面临的主要挑战之一。为了减轻缺乏真正的培训数据，当前的大多数猿类系统采用数据增强方法来生成大规模的人工语料库。鉴于APE数据增强的重要性，我们分别研究了人工语料库的构建方法和人工数据域对猿类模型性能的影响。此外，猿类的难度在不同的机器翻译（MT）系统之间有所不同。我们在困难的猿数据集上研究了最先进的APE模型的输出，以分析现有的APE系统中的问题。首先，我们发现1）具有高质量源文本和机器翻译文本的人工语料库更有效地改善了猿类模型的性能； 2）内域人工训练数据可以更好地改善猿类模型的性能，而无关紧要的外域数据实际上会干扰该模型； 3）现有的APE模型与包含长源文本或高质量机器翻译文本的案例斗争； 4）最先进的猿类模型在语法和语义添加问题上很好地工作，但是输出容易出现实体和语义遗漏误差。

合并个人喜好对于高级机器翻译任务至关重要。尽管机器翻译最近进步，但正确反映个人风格仍然是一项艰巨的任务。在本文中，我们引入了一个个性化的自动后编辑框架来应对这一挑战，该挑战有效地产生了考虑不同个人行为的句子。为了构建此框架，我们首先收集后编辑数据，该数据表示来自Live Machine Translation系统的用户偏好。具体而言，现实世界的用户输入源句子进行翻译，并根据用户的首选样式编辑机器翻译的输出。然后，我们提出了一个模型，该模型结合了APE框架上的歧视器模块和特定于用户的参数。实验结果表明，该方法的表现优于四个不同指标（即BLEU，TER，YISI-1和人类评估）的其他基线模型。

机器翻译（MT）的单词级质量估计（QE）旨在在不参考的情况下找出翻译句子中的潜在翻译错误。通常，关于文字级别量化宽松的传统作品旨在根据文章编辑工作来预测翻译质量，其中通过比较MT句子之间的单词来自动生成单词标签（“ OK”和“ BAD”）。通过翻译错误率（TER）工具包编辑的句子。虽然可以使用后编辑的工作来在一定程度上测量翻译质量，但我们发现它通常与人类对单词是否良好或翻译不良的判断相抵触。为了克服限制，我们首先创建了一个金色基准数据集，即\ emph {hjqe}（人类对质量估计的判断），专家翻译直接注释了对其判断的不良翻译单词。此外，为了进一步利用平行语料库，我们提出了使用两个标签校正策略的自我监督的预训练，即标记改进策略和基于树的注释策略，以使基于TER的人工量化量子ceper更接近\ emph {HJQE}。我们根据公开可用的WMT en-de和en-ZH Corpora进行实质性实验。结果不仅表明我们提出的数据集与人类的判断更加一致，而且还确认了提议的标签纠正策略的有效性。 。}

The word alignment task, despite its prominence in the era of statistical machine translation (SMT), is niche and under-explored today. In this two-part tutorial, we argue for the continued relevance for word alignment. The first part provides a historical background to word alignment as a core component of the traditional SMT pipeline. We zero-in on GIZA++, an unsupervised, statistical word aligner with surprising longevity. Jumping forward to the era of neural machine translation (NMT), we show how insights from word alignment inspired the attention mechanism fundamental to present-day NMT. The second part shifts to a survey approach. We cover neural word aligners, showing the slow but steady progress towards surpassing GIZA++ performance. Finally, we cover the present-day applications of word alignment, from cross-lingual annotation projection, to improving translation.

我们定义了一个名为“扩展单词对齐”的新颖概念，以提高后编辑辅助效率。基于扩展的单词对齐方式，我们进一步提出了一个名为精制单词级量化宽松的新颖任务，该任务输出精制标签和单词级对应关系。与原始单词级别的量化宽松相比，新任务能够直接指出编辑操作，从而提高效率。为了提取扩展单词对齐，我们采用了基于Mbert的监督方法。为了解决精致的单词级量化宽松，我们首先通过训练基于Mbert和XLM-R的序列标记的回归模型来预测原始量化量子标签。然后，我们使用扩展单词对齐来完善原始文字标签。另外，我们提取源差距对应关系，同时获得GAP标签。两种语言对的实验显示了我们方法的可行性，并为我们提供了进一步改进的灵感。

最近，多模式机器翻译（MMT）的研究激增，其中其他模式（例如图像）用于提高文本系统的翻译质量。这种多模式系统的特殊用途是同时机器翻译的任务，在该任务中，已证明视觉上下文可以补充源句子提供的部分信息，尤其是在翻译的早期阶段。在本文中，我们提出了第一个基于变压器的同时MMT体系结构，该体系结构以前尚未在现场探索过。此外，我们使用辅助监督信号扩展了该模型，该信号使用标记的短语区域比对来指导其视觉注意机制。我们在三个语言方向上进行全面的实验，并使用自动指标和手动检查进行彻底的定量和定性分析。我们的结果表明，（i）监督视觉注意力一致地提高了MMT模型的翻译质量，并且（ii）通过监督损失对MMT进行微调，比从SCRATCH训练MMT的MMT可以提高性能。与最先进的模型相比，我们提出的模型可实现多达2.3 bleu和3.5 Meteor点的改善。

Grammatical Error Correction (GEC) is the task of automatically detecting and correcting errors in text. The task not only includes the correction of grammatical errors, such as missing prepositions and mismatched subject-verb agreement, but also orthographic and semantic errors, such as misspellings and word choice errors respectively. The field has seen significant progress in the last decade, motivated in part by a series of five shared tasks, which drove the development of rule-based methods, statistical classifiers, statistical machine translation, and finally neural machine translation systems which represent the current dominant state of the art. In this survey paper, we condense the field into a single article and first outline some of the linguistic challenges of the task, introduce the most popular datasets that are available to researchers (for both English and other languages), and summarise the various methods and techniques that have been developed with a particular focus on artificial error generation. We next describe the many different approaches to evaluation as well as concerns surrounding metric reliability, especially in relation to subjective human judgements, before concluding with an overview of recent progress and suggestions for future work and remaining challenges. We hope that this survey will serve as comprehensive resource for researchers who are new to the field or who want to be kept apprised of recent developments.

在本文中，我们提出了一种新的生成模型，逐步逐步的去噪AutoEncoder（Sundae），不依赖于自回归模型。类似地与去噪扩散技术，在从随机输入开始并从随机输入开始并每次直到收敛改善它们时，日出施加Sundae。我们提出了一个简单的新改进运算符，它比扩散方法更少迭代，同时在定性地在自然语言数据集上产生更好的样本。Sundae在WMT'14英语到德语翻译任务上实现最先进的结果（非自回归方法），在巨大清洁的常见爬网数据集和Python代码的数据集上对无条件语言建模的良好定性结果来自GitHub。通过在模板中填充任意空白模式，Sundae的非自动增加性质开辟了超出左右提示的可能性。

With the recent advance in neural machine translation demonstrating its importance, research on quality estimation (QE) has been steadily progressing. QE aims to automatically predict the quality of machine translation (MT) output without reference sentences. Despite its high utility in the real world, there remain several limitations concerning manual QE data creation: inevitably incurred non-trivial costs due to the need for translation experts, and issues with data scaling and language expansion. To tackle these limitations, we present QUAK, a Korean-English synthetic QE dataset generated in a fully automatic manner. This consists of three sub-QUAK datasets QUAK-M, QUAK-P, and QUAK-H, produced through three strategies that are relatively free from language constraints. Since each strategy requires no human effort, which facilitates scalability, we scale our data up to 1.58M for QUAK-P, H and 6.58M for QUAK-M. As an experiment, we quantitatively analyze word-level QE results in various ways while performing statistical analysis. Moreover, we show that datasets scaled in an efficient way also contribute to performance improvements by observing meaningful performance gains in QUAK-M, P when adding data up to 1.58M.

话语重写旨在恢复核心发挥，并从最新的多转话对话中省略信息。最近，在内部和室外重写设置中，标记而不是线性生成序列的方法已被证明更强。这是由于标记器的较小搜索空间，因为它只能从对话环境中复制令牌。但是，当必须将短语添加到源语言中时，单个上下文跨度不能涵盖这些方法时，这些方法可能会遭受较低的覆盖范围。这可能会以英语等语言发生，这些语言将令牌（例如介词）引入语法重写。我们提出了一个层次上下文标记器（HCT），该标记器通过预测插槽规则（例如，“ baster_”）来减轻此问题，其插槽后来充满了上下文跨度。 HCT（i）使用令牌级的编辑操作和开槽的规则标记源字符串，（ii）填充了对话环境中的跨度的结果规则插槽。此规则标记允许HCT一次添加外在代币和多个跨度。我们进一步集中了规则，以截断规则分布的长尾巴。几个基准测试的实验表明，HCT可以比2个BLEU点胜过最先进的重写系统。

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.

In order to achieve deep natural language understanding, syntactic constituent parsing is a vital step, highly demanded by many artificial intelligence systems to process both text and speech. One of the most recent proposals is the use of standard sequence-to-sequence models to perform constituent parsing as a machine translation task, instead of applying task-specific parsers. While they show a competitive performance, these text-to-parse transducers are still lagging behind classic techniques in terms of accuracy, coverage and speed. To close the gap, we here extend the framework of sequence-to-sequence models for constituent parsing, not only by providing a more powerful neural architecture for improving their performance, but also by enlarging their coverage to handle the most complex syntactic phenomena: discontinuous structures. To that end, we design several novel linearizations that can fully produce discontinuities and, for the first time, we test a sequence-to-sequence model on the main discontinuous benchmarks, obtaining competitive results on par with task-specific discontinuous constituent parsers and achieving state-of-the-art scores on the (discontinuous) English Penn Treebank.

自动编辑后（APE）是减少通过机器翻译（MT）系统或软件辅助翻译产生的原始翻译文本错误的重要补救措施。在本文中，我们提出了一种系统的方法来解决越南人的APE任务。具体来说，我们构建了5M越南翻译和纠正句对的第一个大规模数据集。然后，我们使用由构造的数据集应用强大的神经MT模型来处理APE任务。自动和人类评估的实验结果表明了神经MT模型在处理越南APE任务方面的有效性。

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.

Pre-training is an effective technique for ensuring robust performance on a variety of machine learning tasks. It typically depends on large-scale crawled corpora that can result in toxic or biased models. Such data can also be problematic with respect to copyright, attribution, and privacy. Pre-training with synthetic tasks and data is a promising way of alleviating such concerns since no real-world information is ingested by the model. Our goal in this paper is to understand what makes for a good pre-trained model when using synthetic resources. We answer this question in the context of neural machine translation by considering two novel approaches to translation model pre-training. Our first approach studies the effect of pre-training on obfuscated data derived from a parallel corpus by mapping words to a vocabulary of 'nonsense' tokens. Our second approach explores the effect of pre-training on procedurally generated synthetic parallel data that does not depend on any real human language corpus. Our empirical evaluation on multiple language pairs shows that, to a surprising degree, the benefits of pre-training can be realized even with obfuscated or purely synthetic parallel data. In our analysis, we consider the extent to which obfuscated and synthetic pre-training techniques can be used to mitigate the issue of hallucinated model toxicity.