The long-distance agreement, evidence for syntactic structure, is increasingly used to assess the syntactic generalization of Neural Language Models. Much work has shown that transformers are capable of high accuracy in varied agreement tasks, but the mechanisms by which the models accomplish this behavior are still not well understood. To better understand transformers' internal working, this work contrasts how they handle two superficially similar but theoretically distinct agreement phenomena: subject-verb and object-past participle agreement in French. Using probing and counterfactual analysis methods, our experiments show that i) the agreement task suffers from several confounders which partially question the conclusions drawn so far and ii) transformers handle subject-verb and object-past participle agreements in a way that is consistent with their modeling in theoretical linguistics.
translated by 谷歌翻译
One of the major challenges of machine translation (MT) is ambiguity, which can in some cases be resolved by accompanying context such as an image. However, recent work in multimodal MT (MMT) has shown that obtaining improvements from images is challenging, limited not only by the difficulty of building effective cross-modal representations but also by the lack of specific evaluation and training data. We present a new MMT approach based on a strong text-only MT model, which uses neural adapters and a novel guided self-attention mechanism and which is jointly trained on both visual masking and MMT. We also release CoMMuTE, a Contrastive Multilingual Multimodal Translation Evaluation dataset, composed of ambiguous sentences and their possible translations, accompanied by disambiguating images corresponding to each translation. Our approach obtains competitive results over strong text-only models on standard English-to-French benchmarks and outperforms these baselines and state-of-the-art MMT systems with a large margin on our contrastive test set.
translated by 谷歌翻译
Static subword tokenization algorithms have been an essential component of recent works on language modeling. However, their static nature results in important flaws that degrade the models' downstream performance and robustness. In this work, we propose MANTa, a Module for Adaptive Neural TokenizAtion. MANTa is a differentiable tokenizer trained end-to-end with the language model. The resulting system offers a trade-off between the expressiveness of byte-level models and the speed of models trained using subword tokenization. In addition, our tokenizer is highly explainable since it produces an explicit segmentation of sequences into blocks. We evaluate our pre-trained model on several English datasets from different domains as well as on synthetic noise. We find that MANTa improves robustness to character perturbations and out-of-domain data. We then show that MANTa performs comparably to other models on the general-domain GLUE benchmark. Finally, we show that it is considerably faster than strictly byte-level models.
translated by 谷歌翻译
Recent approaches to drape garments quickly over arbitrary human bodies leverage self-supervision to eliminate the need for large training sets. However, they are designed to train one network per clothing item, which severely limits their generalization abilities. In our work, we rely on self-supervision to train a single network to drape multiple garments. This is achieved by predicting a 3D deformation field conditioned on the latent codes of a generative network, which models garments as unsigned distance fields. Our pipeline can generate and drape previously unseen garments of any topology, whose shape can be edited by manipulating their latent codes. Being fully differentiable, our formulation makes it possible to recover accurate 3D models of garments from partial observations -- images or 3D scans -- via gradient descent. Our code will be made publicly available.
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
We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by few other works. We also demonstrate that model pre-training and sparse scaling using Mixture-of-Experts bring large gains to translation performance. The mined data and models are freely available.
translated by 谷歌翻译
基于概念的解释允许通过用户指定的概念镜头来了解深神经网络（DNN）的预测。现有方法假设说明概念的示例是在DNN潜在空间的固定方向上映射的。当这种情况下，该概念可以用指向该方向的概念激活向量（CAV）表示。在这项工作中，我们建议通过允许概念示例散布在DNN潜在空间中的不同群集中来放松这一假设。然后，每个概念都由DNN潜在空间的区域表示，该区域包括这些簇，我们称为概念激活区域（CAR）。为了使这个想法形式化，我们介绍了基于内核技巧和支持向量分类器的CAV形式主义的扩展。这种汽车形式主义产生了基于全球概念的解释和基于本地概念的特征重要性。我们证明，用径向核建造的汽车解释在潜在空间等法下是不变的。这样，汽车将相同的解释分配给具有相同几何形状的潜在空间。我们进一步证明汽车提供（1）更准确地描述了概念如何散布在DNN的潜在空间中； （2）更接近人类概念注释和（3）基于概念的特征的重要性重要性的全球解释，这些特征的重要性是有意义地相互关联的。最后，我们使用汽车表明DNN可以自主重新发现已知的科学概念，例如前列腺癌分级系统。
translated by 谷歌翻译
现有的数据驱动方法用于披上姿势的人体，尽管有效，但无法处理任意拓扑的服装，并且通常不是端到端的。为了解决这些局限性，我们提出了一条端到端可区分管道，该管道用隐式表面表示服装，并学习以铰接式身体模型的形状和姿势参数为条件的皮肤场。为了限制身体的插入和人工制品，我们提出了一种解释意识的训练数据的预处理策略和新颖的训练损失，在覆盖服装的同时惩罚了自身交流。我们证明，我们的方法可以针对最新方法产生更准确的结果和变形。此外，我们表明我们的方法凭借其端到端的可不同性，可以从图像观察中共同恢复身体和服装参数，这是以前的工作无法做到的。
translated by 谷歌翻译
Angluin的L*算法使用会员资格和等价查询了解了常规语言的最低（完整）确定性有限自动机（DFA）。它的概率近似正确（PAC）版本用足够大的随机会员查询替换等效查询，以使答案获得高级信心。因此，它可以应用于任何类型的（也是非规范）设备，可以将其视为合成自动机的算法，该算法根据观测值抽象该设备的行为。在这里，我们对Angluin的PAC学习算法对通过引入一些噪音从DFA获得的设备感兴趣。更确切地说，我们研究盎格鲁因算法是否会降低噪声并产生与原始设备更接近原始设备的DFA。我们提出了几种介绍噪声的方法：（1）嘈杂的设备将单词的分类W.R.T.倒置。具有很小概率的DFA，（2）嘈杂的设备在询问其分类W.R.T.之前用小概率修改了单词的字母。 DFA和（3）嘈杂的设备结合了W.R.T.单词的分类。 DFA及其分类W.R.T.柜台自动机。我们的实验是在数百个DFA上进行的。直言不讳地表明，我们的主要贡献表明：（1）每当随机过程产生嘈杂的设备时，盎格鲁因算法的行为都很好，（2）但使用结构化的噪声却很差，并且（3）几乎肯定是随机性的产量具有非竞争性语言的系统。
translated by 谷歌翻译
JPEG-XS为具有限制但合理的位率和低延迟的应用提供了低复杂性图像压缩。我们的论文探讨了JPEG-XS在有损耗的数据包网络上的部署。为了保留低延迟，远期误差校正（FEC）被设想为感兴趣的保护机制。尽管JPEG-XS编码词本质上无法扩展，但我们观察到，编码级数的丢失对解码的图像质量的影响有所不同，具体取决于此编码级数是否对应于CodeStream的标题，以使系数显着性信息，还是对低/高频/高频/高频/高频。数据分别。因此，我们提出了一种最佳的最佳误差保护方案，该方案根据渠道损失率和由代码保护的信息类型来适应芦苇 - 固体代码的冗余水平。我们的实验表明，与没有最佳和最佳保护的传输相比，以5％的损耗率将平均误差降低了92％和65％。
translated by 谷歌翻译