Pre-trained language models (PLMs) have exhibited remarkable few-shot learning capabilities when provided a few examples in a natural language prompt as demonstrations of test instances, i.e., in-context learning. However, the performance of in-context learning is susceptible to the choice of prompt format, training examples and the ordering of the training examples. In this paper, we propose a novel nearest-neighbor calibration framework for in-context learning to ease this issue. It is inspired by a phenomenon that the in-context learning paradigm produces incorrect labels when inferring training instances, which provides a useful supervised signal to calibrate predictions. Thus, our method directly augments the predictions with a $k$-nearest-neighbor ($k$NN) classifier over a datastore of cached few-shot instance representations obtained by PLMs and their corresponding labels. Then adaptive neighbor selection and feature regularization modules are introduced to make full use of a few support instances to reduce the $k$NN retrieval noise. Experiments on various few-shot text classification tasks demonstrate that our method significantly improves in-context learning, while even achieving comparable performance with state-of-the-art tuning-based approaches in some sentiment analysis tasks.
translated by 谷歌翻译
端到端语音翻译(E2E-ST)由于其误差传播的潜力,较低的延迟和较少的参数而受到了越来越多的关注。但是,基于神经的方法对该任务的有效性受到可用培训语料库的严重限制,尤其是对于较少或不存在的域中三重障碍培训数据的领域适应性。在本文中,我们提出了一种新型的非参数方法,该方法利用特定于域的文本翻译语料库来实现E2E-ST系统的域适应性。为此,我们首先将一个附加的编码器纳入预先训练的E2E-ST模型中,以实现文本翻译建模,然后通过减少可用三重态训练数据中的通讯表示不匹配来统一解码器的输出表示形式,以实现文本和语音翻译任务。在域适应过程中,引入了K-Nearest-neighbor(KNN)分类器,以使用由域特异性文本翻译语料库构建的外部数据存储器生成最终的翻译分布,而采用通用输出表示来执行相似性搜索。 Europarl-St基准的实验表明,仅涉及内域文本翻译数据时,我们提出的方法在所有翻译方向上平均将基线显着提高了基线,即使表现出强大的强度内域微调方法。
translated by 谷歌翻译
由于其误差传播,延迟较少和更少的参数较少的潜力,端到端语音到文本翻译〜(e2e-st)变得越来越受欢迎。鉴于三联培训语料库$ \ langle演讲,转录,翻译\ rangle $,传统的高质量E2E-ST系统利用$ \ langle演讲,转录\ rangle $配对预先培训模型,然后利用$ \ Langle演讲,翻译\ rangle $配对进一步优化它。然而,该过程仅涉及每个阶段的两个元组数据,并且该松散耦合不能完全利用三重态数据之间的关联。在本文中,我们试图基于语音输入模拟转录和翻译的联合概率,以直接利用这种三重态数据。基于此,我们提出了一种新的正规化方法,用于改进三重态数据中双路分解协议的模型培训,理论上应该是相等的。为实现这一目标,我们将两个Kullback-Leibler发散正规化术语介绍到模型培训目的中,以减少双路径输出概率之间的不匹配。然后,训练有素的模型可以通过预定义的早期停止标签自然地被视为E2E-ST模型。 Must-C基准测试的实验表明,我们所提出的方法在所有8个语言对上显着优于最先进的E2E-ST基线,同时在自动语音识别任务中实现更好的性能。我们的代码在https://github.com/duyichao/e2e -st-tda开放。
translated by 谷歌翻译
我们研究了在循环机器翻译中对人体反馈的在线学习问题,其中人类翻译人员修改了机器生成的翻译,然后使用校正的翻译来改善神经电机翻译(NMT)系统。然而,以前的方法需要在线模型更新或额外的翻译记忆网络来实现高质量的性能,使它们在实践中不灵活和效率低下。在本文中,我们提出了一种新颖的非参数在线学习方法而不改变模型结构。这种方法引入了两个K-Cirelte-邻(KNN)模块:一个模块记住了人类反馈,这是人类翻译人员提供的正确句子,而另一个模块是自适应地平衡历史人体反馈和原始NMT模型的使用。在EMEA和JRC-ACQUIS基准上进行的实验表明,我们所提出的方法对翻译准确性的大量改进,并通过更少的人力校正操作实现更好的适应性能。
translated by 谷歌翻译
在本文中,我们建议将面向任务导向的对话系统作为纯粹的自然语言生成任务,以便充分利用像GPT-2这样的大规模预训练模型,并简化了复杂的光学化预备。然而,直接应用这种方法严重遭受了通过删除了替代令牌而导致的对话实体不一致,以及在微调期间灾害模型的灾难性遗忘问题,导致表现不令人满意。为了缓解这些问题,我们设计了一种新颖的GPT-Adapter-CopyNet网络,它将轻量级适配器和CopyNet模块包含到GPT-2中,以实现转移学习和对话实体生成的更好性能。在DSTC8轨道1基准和多种数据集上进行的实验结果表明,我们的建议方法显着优于基线模型,在自动和人类评估中具有显着性能。
translated by 谷歌翻译
Occupancy information is useful for efficient energy management in the building sector. The massive high-resolution electrical power consumption data collected by smart meters in the advanced metering infrastructure (AMI) network make it possible to infer buildings' occupancy status in a non-intrusive way. In this paper, we propose a deep leaning model called ABODE-Net which employs a novel Parallel Attention (PA) block for building occupancy detection using smart meter data. The PA block combines the temporal, variable, and channel attention modules in a parallel way to signify important features for occupancy detection. We adopt two smart meter datasets widely used for building occupancy detection in our performance evaluation. A set of state-of-the-art shallow machine learning and deep learning models are included for performance comparison. The results show that ABODE-Net significantly outperforms other models in all experimental cases, which proves its validity as a solution for non-intrusive building occupancy detection.
translated by 谷歌翻译
模型压缩(例如修剪和量化)已广泛应用于在资源有限的经典设备上优化神经网络。最近,对变分量子电路(VQC)的兴趣越来越大,即量子计算机上的一种神经网络(又称量子神经网络)。众所周知,近期的量子设备具有高噪声和有限的资源(即量子位,Qubits);但是,如何压缩量子神经网络尚未得到彻底研究。人们可能会认为将经典压缩技术应用于量子场景是很简单的。但是,本文表明,量子和经典神经网络的压缩之间存在差异。根据我们的观察,我们声称必须参与压缩过程。最重要的是,我们提出了第一个系统的框架,即CompVQC,以压缩量子神经网络(QNNS)。在CompVQC中,关键组件是一种新型的压缩算法,该算法基于乘数的交替方向方法(ADMM)。方法。实验证明了COMPVQC的优势,以微不足道的精度下降(<1%)降低了电路深度(几乎超过2.5%),这表现优于其他竞争对手。另一个有前途的事实是,我们的COMPVQC确实可以促进QNN在近期噪声量子设备上的鲁棒性。
translated by 谷歌翻译
普遍认为对抗培训是一种可靠的方法来改善对抗对抗攻击的模型稳健性。但是,在本文中,我们表明,当训练在一种类型的中毒数据时,对抗性培训也可以被愚蠢地具有灾难性行为,例如,$ <1 \%$强大的测试精度,以$> 90 \%$强大的训练准确度在CiFar-10数据集上。以前,在培训数据中,已经成功愚弄了标准培训($ 15.8 \%$标准测试精度,在CIFAR-10数据集中的标准训练准确度为99.9美元,但它们的中毒可以很容易地删除采用对抗性培训。因此,我们的目标是设计一种名为Advin的新型诱导噪声,这是一种不可动摇的培训数据中毒。 Advin不仅可以通过大幅度的利润率降低对抗性培训的鲁棒性,例如,从Cifar-10数据集每次为0.57 \%$ 0.57 \%$ 0.57 \%$ 0.1,但也有效地愚弄标准培训($ 13.1 \%$标准测试准确性$ 100 \%$标准培训准确度)。此外,否则可以应用于防止个人数据(如SELYIES)在没有授权的情况下剥削,无论是标准还是对抗性培训。
translated by 谷歌翻译
Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.
translated by 谷歌翻译
In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.
translated by 谷歌翻译