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。

非自动性变压器（NAT）是文本生成模型的家族，旨在通过并行预测整个句子来减少解码延迟。但是，这种延迟减少牺牲了捕获从左到右的依赖性的能力，从而使NAT学习非常具有挑战性。在本文中，我们介绍了理论和经验分析，以揭示NAT学习的挑战，并提出统一的观点来了解现有的成功。首先，我们表明，简单地通过最大化可能性来训练NAT可以导致边际分布的近似值，但在代币之间降低了所有依赖关系，在该数据集的条件总相关性可以测量删除的信息。其次，我们在统一的框架中正式化了许多以前的目标，并表明他们的成功可以得出结论，以最大程度地提高代理分布的可能性，从而减少了信息损失。实证研究表明，我们的观点可以解释NAT学习中的现象，并指导新培训方法的设计。

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。

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

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, under comparable experiment settings, XLNet outperforms BERT on 20 tasks, often by a large margin, including question answering, natural language inference, sentiment analysis, and document ranking. 1 .

最近非自动增加（NAR）机器翻译最近取得了显着的改进，现在优于一些基准测试的自动增加（AR）模型，为AR推断提供有效的替代方案。然而，虽然AR转换通常使用多语言模型来实现，但是从语言之间的转移和改善的服务效率，多语言NAR模型仍然相对未开发。作为一个示例NAR模型和变压器作为半NAR模型，采用连接员时间分类（CTC），我们展示了多语种NAR的全面实证研究。我们在容量限制下对相关语言与负转移之间的积极转移来测试其能力。随着NAR模型需要蒸馏培训套，我们仔细研究双语与多语种教师的影响。最后，我们适合多语言NAR的缩放法，这使得其相对于AR模型的性能随着模型量表的增加而定量。

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.

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。

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.

最近，非自动增加（NAT）模型并行地预测输出，与自回归（AT）模型相比，实现了产生速度的大量改进。在对原始数据上表现更差的同时，大多数NAT模型都被培训为在教师模型生成的蒸馏数据上的学生模型，称为序列级知识蒸馏。提高模型性能的有效培训策略是自蒸馏混合（SDM）培训，预先训练原始数据模型，通过预先训练的模型本身产生蒸馏数据，最后重新列举模型原始数据和蒸馏数据的组合。在这项工作中，我们的目标是查看NAT模型的SDM，但发现直接采用SDM到NAT模型在翻译质量方面没有改进。通过仔细分析，我们观察失效与教师模型与NAT学生模型的建模和确认偏差相关。基于这些发现，我们提出了一种增强的策略，通过向经典SDM添加两个阶段来提高名为SDMRT的策略：一个是在自蒸馏数据上进行预重磅，另一个是对滤波后的教师蒸馏数据进行微调。我们的结果在多个NAT模型上以0.6至1.2 bleu表示基础。作为另一个奖励，对于迭代细化NAT模型，我们的方法可以在半迭代号内倾斜基线，这意味着2x加速度。

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.

Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However, there is still a significant performance gap between NMT and SiMT. In this work, we propose to leverage monolingual data to improve SiMT, which trains a SiMT student on the combination of bilingual data and external monolingual data distilled by Seq-KD. Preliminary experiments on En-Zh and En-Ja news domain corpora demonstrate that monolingual data can significantly improve translation quality (e.g., +3.15 BLEU on En-Zh). Inspired by the behavior of human simultaneous interpreters, we propose a novel monolingual sampling strategy for SiMT, considering both chunk length and monotonicity. Experimental results show that our sampling strategy consistently outperforms the random sampling strategy (and other conventional typical NMT monolingual sampling strategies) by avoiding the key problem of SiMT -- hallucination, and has better scalability. We achieve +0.72 BLEU improvements on average against random sampling on En-Zh and En-Ja. Data and codes can be found at https://github.com/hexuandeng/Mono4SiMT.

For sequence generation, both autoregressive models and non-autoregressive models have been developed in recent years. Autoregressive models can achieve high generation quality, but the sequential decoding scheme causes slow decoding speed. Non-autoregressive models accelerate the inference speed with parallel decoding, while their generation quality still needs to be improved due to the difficulty of modeling multi-modalities in data. To address the multi-modality issue, we propose Diff-Glat, a non-autoregressive model featured with a modality diffusion process and residual glancing training. The modality diffusion process decomposes the modalities and reduces the modalities to learn for each transition. And the residual glancing sampling further smooths the modality learning procedures. Experiments demonstrate that, without using knowledge distillation data, Diff-Glat can achieve superior performance in both decoding efficiency and accuracy compared with the autoregressive Transformer.

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when the NAT output is closer to other translations. In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. As we train NAT based on the rephraser output rather than the reference sentence, the rephraser output should fit well with the NAT output and not deviate too far from the reference, which can be quantified as reward functions and optimized by reinforcement learning. Experiments on major WMT benchmarks and NAT baselines show that our approach consistently improves the translation quality of NAT. Specifically, our best variant achieves comparable performance to the autoregressive Transformer, while being 14.7 times more efficient in inference.

上下文感知的str方法通常使用内部自回旋（AR）语言模型（LM）。 AR模型的固有局限性动机是采用外部LM的两阶段方法。输入图像上外部LM的条件独立性可能导致其错误地纠正正确的预测，从而导致明显的低效率。我们的方法Parseq使用置换语言建模学习了具有共同权重的内部AR LMS集合。它统一了无上下文的非AR和上下文感知的AR推断，并使用双向上下文统一了迭代的精致。使用合成训练数据，Parseq实现了最新的（SOTA），从而获得了Str基准（精度为91.9％）和更具挑战性的数据集。在对实际数据进行培训时，它建立了新的SOTA结果（精度为96.0％）。 Parseq由于其简单，统一的结构和平行的令牌处理，对准确性与参数计数，拖放和延迟非常最佳。由于其广泛使用了注意力，它对在现实世界图像中常见的任意导向文本具有鲁棒性。代码，预处理的权重和数据可在以下网址提供：https：//github.com/baudm/parseq。

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。

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.

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.

现有的图像字幕的方法通常从左到右生成句子逐字，并在本地上下文中受到限制，包括给定的图像和历史记录生成的单词。在解码过程中，有许多研究目的是利用全球信息，例如迭代改进。但是，它仍然探讨了如何有效，有效地纳入未来的环境。为了回答这个问题，受到非自动回归图像字幕（NAIC）的启发，可以通过修改后的掩码操作利用两侧关系，我们的目标是将此进步嫁接到常规的自动回归图像字幕（AIC）模型，同时保持推理效率而无需进行推理效率额外的时间成本。具体而言，首先对AIC和NAIC模型结合了共享的视觉编码器，迫使视觉编码器包含足够有效的未来上下文。然后鼓励AIC模型捕获NAIC模型在其不自信的单词上互换的跨层互换的因果动态，该单词遵循教师学生的范式，并通过分配校准训练目标进行了优化。经验证据表明，我们所提出的方法清楚地超过了自动指标和人类评估的最新基线，对MS COCO基准测试。源代码可在以下网址获得：https：//github.com/feizc/future-caption。

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。