Neural machine translation (NMT) has become the de-facto standard in real-world machine translation applications. However, NMT models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user trust. It becomes thus crucial to implement effective preventive strategies to guarantee their proper functioning. In this paper, we address the problem of hallucination detection in NMT by following a simple intuition: as hallucinations are detached from the source content, they exhibit encoder-decoder attention patterns that are statistically different from those of good quality translations. We frame this problem with an optimal transport formulation and propose a fully unsupervised, plug-in detector that can be used with any attention-based NMT model. Experimental results show that our detector not only outperforms all previous model-based detectors, but is also competitive with detectors that employ large models trained on millions of samples.
translated by 谷歌翻译
As more and more conversational and translation systems are deployed in production, it is essential to implement and to develop effective control mechanisms guaranteeing their proper functioning and security. An essential component to ensure safe system behavior is out-of-distribution (OOD) detection, which aims at detecting whether an input sample is statistically far from the training distribution. Although OOD detection is a widely covered topic in classification tasks, it has received much less attention in text generation. This paper addresses the problem of OOD detection for machine translation and dialog generation from an operational perspective. Our contributions include: (i) RAINPROOF a Relative informAItioN Projection ODD detection framework; and (ii) a more operational evaluation setting for OOD detection. Surprisingly, we find that OOD detection is not necessarily aligned with task-specific measures. The OOD detector may filter out samples that are well processed by the model and keep samples that are not, leading to weaker performance. Our results show that RAINPROOF breaks this curse and achieve good results in OOD detection while increasing performance.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
能够替换人类判断的自动评估指标对于允许快速开发新方法至关重要。因此，许多研究工作集中在制定此类指标上。在这项工作中，我们退后一步，通过比较现有的自动指标和人类指标的身体来分析最近的进度。由于指标是根据它们的排名系统的方式使用的，因此我们比较系统排名空间中的指标。我们广泛的统计分析揭示了令人惊讶的发现：自动指标 - 新老 - 与彼此相比，比人类更相似。自动指标不是互补的，等级系统也类似。令人惊讶的是，人类指标彼此相互预测要比所有用于预测人类指标的自动指标的组合要好得多。令人惊讶的是，人类指标通常被设计为独立，以捕获质量的不同方面，例如内容保真度或可读性。我们对这些发现和建议进行讨论，以在评估领域的未来工作。
translated by 谷歌翻译
自动故事生成（ASG）的研究在很大程度上依赖于人类和自动评估。但是，尚无共识在哪些人类评估标准上使用，也没有分析自动标准与它们相关的良好状况。在本文中，我们建议重新评估ASG评估。我们介绍了由社会科学文学精心促进的6种正交和全面的人类标准。我们还提出了汉娜（Hanna），这是一个由10种不同ASG系统制作的1,056个故事的注释数据集。汉娜（Hanna）允许我们定量评估72个自动指标与人类标准的相关性。我们的分析强调了ASG当前指标的弱点，并使我们能够为ASG评估提出实用建议。
translated by 谷歌翻译
共同信息（MI）已被广泛用作训练神经网络的损失正规化程序。当学习高维数据的分解或压缩表示时，这特别有效。但是，差异熵（DE）是信息的另一种基本衡量标准，在神经网络培训中尚未发现广泛使用。尽管DE提供了比MI的可能更广泛的应用程序，但现成的DE估计器要么是非可区分的，在计算上是棘手的，要么无法适应基础分布的变化。这些缺点使它们无法在神经网络培训中用作正规化器。为了解决DE先前提出的估计器中的缺点，我们在这里介绍了刀具，这是一个完全参数化的，基于DE的基于核的估计器。我们方法的灵活性还使我们能够为条件（离散变量或连续变量）以及MI构建基于刀的估计器。我们从经验上验证了高维合成数据的方法，并进一步应用它来指导神经网络的现实任务培训。我们对各种任务的实验，包括视觉域的适应性，文本公平分类和文本微调，证明了基于刀的估计的有效性。代码可以在https://github.com/g-pichler/knife上找到。
translated by 谷歌翻译
2021-12-06
数据增强是自然语言处理（NLP）模型的鲁棒性评估的重要组成部分，以及增强他们培训的数据的多样性。在本文中，我们呈现NL-Cogmenter，这是一种新的参与式Python的自然语言增强框架，它支持创建两个转换（对数据的修改）和过滤器（根据特定功能的数据拆分）。我们描述了框架和初始的117个变换和23个过滤器，用于各种自然语言任务。我们通过使用其几个转换来分析流行自然语言模型的鲁棒性来证明NL-Upmenter的功效。基础架构，Datacards和稳健性分析结果在NL-Augmenter存储库上公开可用（\ url {https://github.com/gem-benchmark/nl-augmenter}）。
translated by 谷歌翻译
通过人类注释评估自然语言生成系统的质量非常昂贵。此外，人类注释运动是耗时的，包括不可重复使用的人工劳动力。在实践中，研究人员依赖于自动指标作为质量的代理。在过去的十年中，已经介绍了许多基于字符串的度量（例如，BLEU）。但是，这种指标通常依赖于完全匹配，因此，不强大地处理同义词。在本文中，我们介绍了InfolmM一系列未经培训的指标，可以被视为基于字符串的度量标准，该度量可以通过预先接受培训的屏蔽语言模型来解决上述漏洞。这家指标族也利用信息措施，允许改编Infolmm对各种评估标准。使用直接评估，我们展示Infolmm在概要和Data2Text生成的许多配置中实现了统计上显着的改进和超过10美元的相关点。
translated by 谷歌翻译
Recent advances in deep learning have enabled us to address the curse of dimensionality (COD) by solving problems in higher dimensions. A subset of such approaches of addressing the COD has led us to solving high-dimensional PDEs. This has resulted in opening doors to solving a variety of real-world problems ranging from mathematical finance to stochastic control for industrial applications. Although feasible, these deep learning methods are still constrained by training time and memory. Tackling these shortcomings, Tensor Neural Networks (TNN) demonstrate that they can provide significant parameter savings while attaining the same accuracy as compared to the classical Dense Neural Network (DNN). In addition, we also show how TNN can be trained faster than DNN for the same accuracy. Besides TNN, we also introduce Tensor Network Initializer (TNN Init), a weight initialization scheme that leads to faster convergence with smaller variance for an equivalent parameter count as compared to a DNN. We benchmark TNN and TNN Init by applying them to solve the parabolic PDE associated with the Heston model, which is widely used in financial pricing theory.
translated by 谷歌翻译
Training a very deep neural network is a challenging task, as the deeper a neural network is, the more non-linear it is. We compare the performances of various preconditioned Langevin algorithms with their non-Langevin counterparts for the training of neural networks of increasing depth. For shallow neural networks, Langevin algorithms do not lead to any improvement, however the deeper the network is and the greater are the gains provided by Langevin algorithms. Adding noise to the gradient descent allows to escape from local traps, which are more frequent for very deep neural networks. Following this heuristic we introduce a new Langevin algorithm called Layer Langevin, which consists in adding Langevin noise only to the weights associated to the deepest layers. We then prove the benefits of Langevin and Layer Langevin algorithms for the training of popular deep residual architectures for image classification.
translated by 谷歌翻译