通过最大似然估计（MLE）训练的文本生成模型遭受了臭名昭著的暴露偏见问题，而生成的对抗网络（GAN）被证明具有解决方案的潜力。现有的语言gans采用估计器，例如增强或连续放松来模型单词分布。此类估计器的固有局限性导致当前模型依赖于预训练技术（MLE预训练或预训练的嵌入）。但是，由于其先前尝试的性能较差，因此很少探索没有这些局限性的代表建模方法。我们的分析表明，无效的采样方法和不健康的梯度是其不令人满意的性能的主要因素。在这项工作中，我们提出了两种解决这些问题的技术：辍学抽样和完全归一化的LSTM。基于这两种技术，我们提出了初始gan，其参数是完全初始初始初始初始初始初始初始初始化的。此外，我们引入了新的评估度量，覆盖率最少，以更好地评估生成的样品的质量。实验结果表明，Initialgan的表现都优于MLE和其他比较模型。据我们所知，这是GAN语言第一次在没有任何预训练技术的情况下胜过MLE。

通过大型预训练模型传输学习已经改变了自然语言处理中当前应用程序的景观（NLP）。最近的最佳优化，结合了两个预先训练的模型，BERT和GPT-2的变形AutoEncoder（VAE），并且其与生成的逆境网络（GANs）的组合已被证明是生产小说，但非常人性化的文本。 Optimus和GAN组合避免了GAN到文本的离散领域的麻烦，并防止了标准最大似然方法的曝光偏差。我们将GAN的培训结合在潜在的空间中，并为单词生成的Optimus解码器的FineTuning。这种方法可以让我们模拟句子的高级功能，以及低级Word-By-Word生成。我们通过利用GPT-2的结构以及将基于熵的内在动机奖励添加到质量和多样性之间的平衡来使用加强学习（RL）。我们基准测试VAE-GaN模型的结果，并显示了我们RL FineTuning在三个广泛使用的文本生成数据集中带来的改进，结果结果大大超越了当前最先进的所生成文本的质量。

控制模型生成不同类别的文本是一个挑战的任务，越来越多的关注。最近，生成的对抗性网（GAN）在类别文本生成中显示了有希望的结果。然而，由GAN产生的文本通常遭受模式崩溃和培训不稳定的问题。为了避免上述问题，我们提出了一种名为Categary Impare变分频神经网络（Catvrnn）的小说模型，这是由多任务学习的启发。在我们的模型中，生成和分类是同时培训的，旨在产生不同类别的文本。此外，当分类任务适当时，使用多任务学习可以提高生成文本的质量。并且我们提出了一种初始化Catvrnn的隐藏状态的函数，以强制模型生成特定类别的文本。三个数据集上的实验结果表明，我们的模型可以在基于几种最先进的文本生成方法中，以类别的基于GAN的生成文本的质量。

This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called "natural" language. Nevertheless, adversarial text generation is not a simple task as its foremost architecture, the Generative Adversarial Networks, were designed to cope with continuous information (image) instead of discrete data (text). Thus, most works are based on three possible options, i.e., Gumbel-Softmax differentiation, Reinforcement Learning, and modified training objectives. All alternatives are reviewed in this survey as they present the most recent approaches for generating text using adversarial-based techniques. The selected works were taken from renowned databases, such as Science Direct, IEEEXplore, Springer, Association for Computing Machinery, and arXiv, whereas each selected work has been critically analyzed and assessed to present its objective, methodology, and experimental results.

As a new way of training generative models, Generative Adversarial Net (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. However, it has limitations when the goal is for generating sequences of discrete tokens. A major reason lies in that the discrete outputs from the generative model make it difficult to pass the gradient update from the discriminative model to the generative model. Also, the discriminative model can only assess a complete sequence, while for a partially generated sequence, it is nontrivial to balance its current score and the future one once the entire sequence has been generated. In this paper, we propose a sequence generation framework, called SeqGAN, to solve the problems. Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update. The RL reward signal comes from the GAN discriminator judged on a complete sequence, and is passed back to the intermediate state-action steps using Monte Carlo search. Extensive experiments on synthetic data and real-world tasks demonstrate significant improvements over strong baselines.

Automated audio captioning is a cross-modal translation task for describing the content of audio clips with natural language sentences. This task has attracted increasing attention and substantial progress has been made in recent years. Captions generated by existing models are generally faithful to the content of audio clips, however, these machine-generated captions are often deterministic (e.g., generating a fixed caption for a given audio clip), simple (e.g., using common words and simple grammar), and generic (e.g., generating the same caption for similar audio clips). When people are asked to describe the content of an audio clip, different people tend to focus on different sound events and describe an audio clip diversely from various aspects using distinct words and grammar. We believe that an audio captioning system should have the ability to generate diverse captions, either for a fixed audio clip, or across similar audio clips. To this end, we propose an adversarial training framework based on a conditional generative adversarial network (C-GAN) to improve diversity of audio captioning systems. A caption generator and two hybrid discriminators compete and are learned jointly, where the caption generator can be any standard encoder-decoder captioning model used to generate captions, and the hybrid discriminators assess the generated captions from different criteria, such as their naturalness and semantics. We conduct experiments on the Clotho dataset. The results show that our proposed model can generate captions with better diversity as compared to state-of-the-art methods.

产生人类想要的声音效果是一个重要的话题。但是，在这一领域，很少有研究声音发电。在这项研究中，我们调查了以文本提示为条件的声音，并提出了一个新型的文本对生成框架，该框架由文本编码器组成，矢量量化了变异自动编码器（VQ-VAE），解码器和歌手。该框架首先使用解码器将从文本编码器提取的文本特征传递到借助VQ-VAE的MEL光谱图中，然后使用Vocoder将生成的MEL光谱图转换为波形。我们发现，解码器显着影响发电性能。因此，我们专注于在这项研究中设计一个好的解码器。我们从传统的自动回解码器开始，该解码器已被证明是以前的Sound Generation Works中的最先进方法。但是，AR解码器始终按顺序预测MEL-SPECTROGIN图令牌，这引入了单向偏见和错误问题的积累。此外，使用AR解码器，声音生成时间随着声音持续时间线性增加。为了克服AR解码器引入的缺点，我们提出了一个基于离散扩散模型的非自动回形解码器，称为DiffSound。具体而言，DIFFSOUND可以在一个步骤中预测所有MEL光谱图令牌，然后在下一步中完善预测的令牌，因此可以在几个步骤后获得最优于预测的结果。我们的实验表明，与AR解码器相比，我们提出的差异不仅产生更好的文本到单一生成结果，而且还具有更快的生成速度，例如MOS：3.56 \ textit {v.s} 2.786，并且生成速度为五个比AR解码器快的时间。

原则上，将变异自动编码器（VAE）应用于顺序数据提供了一种用于控制序列生成，操纵和结构化表示学习的方法。但是，训练序列VAE具有挑战性：自回归解码器通常可以解释数据而无需使用潜在空间，即后置倒塌。为了减轻这种情况，最新的模型通过将均匀的随机辍学量应用于解码器输入来削弱强大的解码器。从理论上讲，我们表明，这可以消除解码器输入提供的点式互信息，该信息通过利用潜在空间来补偿。然后，我们提出了一种对抗性训练策略，以实现基于信息的随机辍学。与标准文本基准数据集上的均匀辍学相比，我们的目标方法同时提高了序列建模性能和潜在空间中捕获的信息。

我们考虑了自动生成音乐文本描述的新颖任务。与其他完善的文本生成任务（例如图像标题）相比，富裕的音乐和文本数据集的稀缺性使其成为更具挑战性的任务。在本文中，我们利用众包音乐评论来构建一个新的数据集，并提出一个序列到序列模型以生成音乐的文本描述。更具体地说，我们将扩张的卷积层用作编码器的基本组成部分，基于内存的复发性神经网络作为解码器。为了增强生成文本的真实性和主题，我们进一步建议用歧视者和新的主题评估者微调模型。为了衡量生成的文本的质量，我们还提出了两个新的评估指标，它们比人类评估比传统指标（例如BLEU）更加一致。实验结果验证了我们的模型能够在包含原始音乐的主题和内容信息的同时产生流利而有意义的评论。

多年来，最新的（SOTA）图像字幕方法已在某些评估指标（例如苹果酒）上取得了令人鼓舞的结果。但是，最近的发现表明，这些方法生成的字幕往往会偏向“平均”字幕，该字幕仅捕获训练语料库中最通用的模式（又称语言模式），即所谓的模式崩溃问题。受其影响的影响，生成的标题在多样性上受到限制，通常不如人类做出的自然图像描述。在本文中，我们试图通过提出离散模式学习（DML）范式来避免此问题。我们的创新想法是探索训练字幕语料库中的丰富模式，以学习一组“模式嵌入”，并进一步使用它们来控制现有图像字幕模型生成的字幕模式。具体而言，提出的DML优化了由图像条件的离散变异自动编码器（CDVAE）分支和模式条件的图像字幕（MIC）分支组成的双重体系结构。 CDVAE分支将每个图像标题映射到存储在学习的代码簿中的模式嵌入之一，并接受了纯粹的非自动性生成目标训练，以使模式与众不同和代表性。可以简单地从现有的图像字幕模型中修改麦克风分支，其中将模式嵌入添加到原始单词嵌入作为控制信号中。在实验中，我们将提出的DML应用于两个广泛使用的图像字幕模型，即变压器和AOANET。结果表明，学习模式嵌入成功促进了这些模型，以不同模式生成高质量的图像标题，进一步为MSCOCO数据集的多样性和质量提供了更好的性能。

与CNN的分类，分割或对象检测相比，生成网络的目标和方法根本不同。最初，它们不是作为图像分析工具，而是生成自然看起来的图像。已经提出了对抗性训练范式来稳定生成方法，并已被证明是非常成功的 - 尽管绝不是第一次尝试。本章对生成对抗网络（GAN）的动机进行了基本介绍，并通​​过抽象基本任务和工作机制并得出了早期实用方法的困难来追溯其成功的道路。将显示进行更稳定的训练方法，也将显示出不良收敛及其原因的典型迹象。尽管本章侧重于用于图像生成和图像分析的gan，但对抗性训练范式本身并非特定于图像，并且在图像分析中也概括了任务。在将GAN与最近进入场景的进一步生成建模方法进行对比之前，将闻名图像语义分割和异常检测的架构示例。这将允许对限制的上下文化观点，但也可以对gans有好处。

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to downstream NLP tasks, they generally require large amounts of compute to be effective. As an alternative, we propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network. Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not. Thorough experiments demonstrate this new pre-training task is more efficient than MLM because the task is defined over all input tokens rather than just the small subset that was masked out. As a result, the contextual representations learned by our approach substantially outperform the ones learned by BERT given the same model size, data, and compute. The gains are particularly strong for small models; for example, we train a model on one GPU for 4 days that outperforms GPT (trained using 30x more compute) on the GLUE natural language understanding benchmark. Our approach also works well at scale, where it performs comparably to RoBERTa and XLNet while using less than 1/4 of their compute and outperforms them when using the same amount of compute.

本文对过去二十年来对自然语言生成（NLG）的研究提供了全面的审查，特别是与数据到文本生成和文本到文本生成深度学习方法有关，以及NLG的新应用技术。该调查旨在（a）给出关于NLG核心任务的最新综合，以及该领域采用的建筑;（b）详细介绍各种NLG任务和数据集，并提请注意NLG评估中的挑战，专注于不同的评估方法及其关系;（c）强调一些未来的强调和相对近期的研究问题，因为NLG和其他人工智能领域的协同作用而增加，例如计算机视觉，文本和计算创造力。

条件生成的对抗性网络（CGAN）通过将类信息纳入GaN来生成现实图像。虽然最受欢迎的CGANS是一种辅助分类器GAN，但众所周知，随着数据集中的类别的数量增加，培训acgan正在挑战。偶数还倾向于产生缺乏多样性的容易甲型样本。在本文中，我们介绍了两种治疗方法。首先，我们识别分类器中的梯度爆炸可能会导致早期训练中的不良崩溃，并将输入向量投影到单元间隔子上可以解决问题。其次，我们提出了数据到数据跨熵丢失（D2D-CE）来利用类标记的数据集中的关系信息。在这个基础上，我们提出了重新启动的辅助分类器生成对抗网络（Reacgan）。实验结果表明，Reacgan在CIFAR10，微小想象成，CUB200和Imagenet数据集上实现了最先进的生成结果。我们还验证了来自可分辨率的增强的ReacanggaN的利益，以及D2D-CE与Stylegan2架构协调。模型权重和提供代表性CGANS实现的软件包和我们纸上的所有实验都可以在https://github.com/postech-cvlab/pytorch-studiogan获得。

Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always rely on auto-regressive decoding. However, previous methods using contrastive learning in neural text generation usually lead to inferior performance. In this paper, we analyse the underlying reasons and propose a new Contrastive Neural Text generation framework, CoNT. CoNT addresses bottlenecks that prevent contrastive learning from being widely adopted in generation tasks from three aspects -- the construction of contrastive examples, the choice of the contrastive loss, and the strategy in decoding. We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation. Experimental results show that CoNT clearly outperforms the conventional training framework on all the ten benchmarks with a convincing margin. Especially, CoNT surpasses previous the most competitive contrastive learning method for text generation, by 1.50 BLEU on machine translation and 1.77 ROUGE-1 on summarization, respectively. It achieves new state-of-the-art on summarization, code comment generation (without external data) and data-to-text generation.

Mode collapse is still a major unsolved problem in generative adversarial networks. In this work, we analyze the causes of mode collapse from a new perspective. Due to the nonuniform sampling in the training process, some sub-distributions can be missed while sampling data. Therefore, the GAN objective can reach the minimum when the generated distribution is not the same as the real one. To alleviate the problem, we propose a global distribution fitting (GDF) method by a penalty term to constrain generated data distribution. On the basis of not changing the global minimum of the GAN objective, GDF will make it harder to reach the minimum value when the generated distribution is not the same as the real one. Furthermore, we also propose a local distribution fitting (LDF) method to cope with the situation that the real distribution is unknown. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.

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。

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyperparameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.

常规域中的文本到图像生成长期以来一直是一个开放问题，这需要强大的生成模型和跨模型理解。我们提出CogView，一个带VQ-VAE牌器的40亿参数变压器来推进此问题。我们还展示了各种下游任务的FineTuning策略，例如，风格学习，超分辨率，文本图像排名和时装设计，以及稳定预制雷岭的方法，例如，消除南损失。Cogview在模糊的MS Coco DataSet上实现最先进的FID，优于以前的基于GAN的模型和最近类似的工作Dall-e。

这是一门专门针对STEM学生开发的介绍性机器学习课程。我们的目标是为有兴趣的读者提供基础知识，以在自己的项目中使用机器学习，并将自己熟悉术语作为进一步阅读相关文献的基础。在这些讲义中，我们讨论受监督，无监督和强化学习。注释从没有神经网络的机器学习方法的说明开始，例如原理分析，T-SNE，聚类以及线性回归和线性分类器。我们继续介绍基本和先进的神经网络结构，例如密集的进料和常规神经网络，经常性的神经网络，受限的玻尔兹曼机器，（变性）自动编码器，生成的对抗性网络。讨论了潜在空间表示的解释性问题，并使用梦和对抗性攻击的例子。最后一部分致力于加强学习，我们在其中介绍了价值功能和政策学习的基本概念。