SoftMax是在致正面规范化的语言处理时现代神经网络的事实标准。然而，通过在词汇中产生致密概率分布，在每个生成步骤中具有非零机会，导致文本生成中的各种报告的问题。$ \ alpha $ - 彼得德·等（2019年，Arxiv：1905.05702）解决了这个问题，但比Softmax更慢。在本文中，我们提出了一种替代$ \ Alpha $ -Temax，它保持其良性特性，但与Optimized SoftMax一样快，并在机器翻译任务中实现PAR或更好的性能。

Reranking methods in machine translation aim to close the gap between common evaluation metrics (e.g. BLEU) and maximum likelihood learning and decoding algorithms. Prior works address this challenge by training models to rerank beam search candidates according to their predicted BLEU scores, building upon large models pretrained on massive monolingual corpora -- a privilege that was never made available to the baseline translation model. In this work, we examine a simple approach for training rerankers to predict translation candidates' BLEU scores without introducing additional data or parameters. Our approach can be used as a clean baseline, decoupled from external factors, for future research in this area.

After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, which inherently makes it difficult to estimate the right probability distribution over next tokens. Yet around this point, these models have identified a simple, loss-minimising behaviour: to output the unigram distribution of the target training corpus. The use of such a crude heuristic raises the question: Rather than wasting precious compute resources and model capacity for learning this strategy at early training stages, can we initialise our models with this behaviour? Here, we show that we can effectively endow our model with a separate module that reflects unigram frequency statistics as prior knowledge. Standard neural language generation architectures offer a natural opportunity for implementing this idea: by initialising the bias term in a model's final linear layer with the log-unigram distribution. Experiments in neural machine translation demonstrate that this simple technique: (i) improves learning efficiency; (ii) achieves better overall performance; and (iii) appears to disentangle strong frequency effects, encouraging the model to specialise in non-frequency-related aspects of language.

我们介绍了一种新的分布式策略梯度算法，并表明它在优化机器翻译模型时，在培训稳定性和概括性绩效方面都优于现有的奖励感知培训程序，例如增强，最低风险培训（MRT）和近端政策优化（PPO）。我们称之为MAD的算法（由于在重要性加权计算中使用平均绝对偏差），它分布式数据生成器在Worker节点上每个源句子对多个候选者进行采样，而中心学习者则更新了策略。 MAD取决于两个降低差异策略：（1）一种有条件的奖励归一化方法，可确保每个源句子都具有正面和负面奖励翻译示例，以及（2）一种新的强大重要性加权方案，充当条件性熵正常化器。在各种翻译任务上进行的实验表明，使用MAD算法在使用贪婪的解码和梁搜索时，使用MAD算法学到的策略表现良好，并且学到的政策对训练过程中使用的特定奖励很敏感。

SoftMax函数广泛用于人工神经网络，用于多级分类问题，其中SoftMax变换强制执行输出为正和总和，并且相应的损耗功能允许使用最大似然原理来优化模型。然而，Softmax留下了大幅的损失函数，以便在高维分类方面进行优化操作，这导致在一定程度上的低性能。在本文中，我们提供了一种对简单简洁的软制态变体，即稀疏-Softmax的实证研究，以减轻在高维分类问题方面的传统软邮件中发生的问题。我们在几个跨学科任务中评估了我们的方法，实验结果表明，Soparse-SoftMax更简单，更快，并产生比基线模型更好的结果。

神经自回归序列模型涂抹许多可能​​序列之间的概率，包括退化的序列，例如空或重复序列。在这项工作中，我们解决了一个特定的情况，其中模型为不合理的短序列分配高概率。我们定义了量化速率以量化此问题。在确认神经机翻译中高度过度的过天气后，我们建议明确地减少培训期间的过天平率。我们进行一组实验来研究建议的正规化对模型分布和解码性能的影响。我们使用神经电脑翻译任务作为测试用，并考虑三个不同大小的不同数据集。我们的实验显示了三个主要结果。首先，我们可以通过调整正规化的强度来控制模型的过天平率。其次，通过提高过度损失贡献，令牌的概率和等级在不应该是它的位置下降。第三，所提出的正则化影响光束搜索的结果，特别是当使用大梁时。用大梁的翻译质量（在BLEU中测量）的降解显着减少了较低的过天速速率，但与较小光束尺寸相比的劣化仍有剩余状态。从这些观察中，我们得出结论，高度过度的过度性是神经自回归模型中过于可能的短序列的退化情况背后的主要原因。

嘈杂的频道模型在神经机翻译（NMT）中特别有效。然而，最近的方法如“波束搜索和重新划分”（BSR）在推理期间引起了大量的计算开销，使实际应用不可行。我们的目标是建立一个摊销嘈杂的频道NMT模型，使得从它贪婪解码将生成转换，以最大化与使用BSR生成的翻译相同的奖励。我们尝试三种方法：知识蒸馏，1阶梯偏差仿制学习和Q学习。第一方法获得来自伪语料库的噪声信道信号，后两种方法旨在直接针对嘈杂的通道MT奖励优化。所有三种级别的速度推动速度推断为1-2级。对于所有三种方法，所生成的翻译无法实现与BSR相当的奖励，但BLEU近似的翻译质量类似于BSR产生的翻译的质量。

Large pretrained language models generate fluent text but are notoriously hard to controllably sample from. In this work, we study constrained sampling from such language models: generating text that satisfies user-defined constraints, while maintaining fluency and the model's performance in a downstream task. We propose MuCoLa -- a sampling procedure that combines the log-likelihood of the language model with arbitrary (differentiable) constraints in a single energy function, and then generates samples in a non-autoregressive manner. Specifically, it initializes the entire output sequence with noise and follows a Markov chain defined by Langevin Dynamics using the gradients of the energy function. We evaluate MuCoLa on text generation with soft and hard constraints as well as their combinations obtaining significant improvements over competitive baselines for toxicity avoidance, sentiment control, and keyword-guided generation.

令牌词汇的选择会影响机器翻译的性能。本文旨在弄清楚什么是良好的词汇，以及没有试用培训的最佳词汇。为了回答这些问题，我们首先为从信息理论的角度提供了对词汇的作用的替代理解。这是由此激励，我们制定了词汇化的追求 - 找到了具有正确尺寸的最佳令牌词典 - 作为最佳运输（OT）问题。我们提出Volt，简单而有效的解决方案，没有试用培训。经验结果表明，在不同场景中，Volt优于广泛使用的词汇，包括WMT-14英语 - 德语和TED的52翻译方向。例如，伏特达到近70％的词汇量减少和英语 - 德语翻译中的0.5个BLEU增益。此外，与BPE搜索相比，Volt在英语 - 德语翻译中将搜索时间从384 GPU小时从384 GPU小时到30 GPU小时。代码在https://github.com/jingjing-nlp/volt上获得。

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.

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.

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。

在传统的视觉问题（VQG）中，大多数图像具有多个概念（例如，对象和类别），可以生成问题，但培训模型以模仿培训数据中给出的任意选择概念。这使得训练困难并且还造成评估问题 - 对于大多数图像而言，存在多个有效问题，但人类参考资料只捕获一个或多个。我们呈现指导视觉问题 - VQG的变体，它根据对问题类型和应该探索的对象的期望来解决基于分类信息的问题生成器。我们提出了两个变体：（i）明确指导的模型，使演员（人机或自动化）能够选择哪些对象和类别来生成问题; （ii）基于离散潜在变量的基于离散潜变量，了解了一个隐式导游的模型，该模型将了解条件的哪些对象和类别。在答案类别增强VQA数据集上评估所提出的模型，我们的定量结果显示了对现有技术的大大改进（超过9bleu-4增加）。人类评估验证指导有助于生成语法相干的问题，并与给定的图像和对象相关。

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。

Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and multiple segmentations are possible even with the same vocabulary. The question addressed in this paper is whether it is possible to harness the segmentation ambiguity as a noise to improve the robustness of NMT. We present a simple regularization method, subword regularization, which trains the model with multiple subword segmentations probabilistically sampled during training. In addition, for better subword sampling, we propose a new subword segmentation algorithm based on a unigram language model. We experiment with multiple corpora and report consistent improvements especially on low resource and out-of-domain settings.

Minimum Bayesian Risk Decoding (MBR) emerges as a promising decoding algorithm in Neural Machine Translation. However, MBR performs poorly with label smoothing, which is surprising as label smoothing provides decent improvement with beam search and improves generality in various tasks. In this work, we show that the issue arises from the un-consistency of label smoothing on the token-level and sequence-level distributions. We demonstrate that even though label smoothing only causes a slight change in the token-level, the sequence-level distribution is highly skewed. We coin the issue \emph{distributional over-smoothness}. To address this issue, we propose a simple and effective method, Distributional Cooling MBR (DC-MBR), which manipulates the entropy of output distributions by tuning down the Softmax temperature. We theoretically prove the equivalence between pre-tuning label smoothing factor and distributional cooling. Experiments on NMT benchmarks validate that distributional cooling improves MBR's efficiency and effectiveness in various settings.

Despite considerable advances in neural language modeling, it remains an open question what the best decoding strategy is for text generation from a language model (e.g. to generate a story). The counter-intuitive empirical observation is that even though the use of likelihood as training objective leads to high quality models for a broad range of language understanding tasks, maximization-based decoding methods such as beam search lead to degeneration -output text that is bland, incoherent, or gets stuck in repetitive loops.To address this we propose Nucleus Sampling, a simple but effective method to draw considerably higher quality text out of neural language models than previous decoding strategies. Our approach avoids text degeneration by truncating the unreliable tail of the probability distribution, sampling from the dynamic nucleus of tokens containing the vast majority of the probability mass. To properly examine current maximization-based and stochastic decoding methods, we compare generations from each of these methods to the distribution of human text along several axes such as likelihood, diversity, and repetition. Our results show that (1) maximization is an inappropriate decoding objective for openended text generation, (2) the probability distributions of the best current language models have an unreliable tail which needs to be truncated during generation and (3) Nucleus Sampling is currently the best available decoding strategy for generating long-form text that is both high-quality -as measured by human evaluation -and as diverse as human-written text.Context: In a shocking finding, scientist discovered a herd of unicorns living in a remote, previously unexplored valley, in the Andes Mountains. Even more surprising to the researchers was the fact that the unicorns spoke perfect English.

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。

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.

FAIRSEQ is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and supports distributed training across multiple GPUs and machines. We also support fast mixed-precision training and inference on modern GPUs. A demo video can be found here: https://www.youtube. com/watch?v=OtgDdWtHvto.