A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical word-analogy task into the visual domain. Given a triplet of images, the task is to select an image candidate B' that completes the analogy (A to A' is like B to what?). Unlike previous work on visual analogy that focused on simple image transformations, we tackle complex analogies requiring understanding of scenes. We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies. Crowdsourced annotations for a sample of the data indicate that humans agree with the dataset label ~80% of the time (chance level 25%). Furthermore, we use human annotations to create a gold-standard dataset of 3,820 validated analogies. Our experiments demonstrate that state-of-the-art models do well when distractors are chosen randomly (~86%), but struggle with carefully chosen distractors (~53%, compared to 90% human accuracy). We hope our dataset will encourage the development of new analogy-making models. Website: https://vasr-dataset.github.io/

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as important as typically thought for pretrained language models. We introduce PAPA, a new probing method that replaces the input-dependent attention matrices with constant ones -- the average attention weights over multiple inputs. We use PAPA to analyze several established pretrained Transformers on six downstream tasks. We find that without any input-dependent attention, all models achieve competitive performance -- an average relative drop of only 8% from the probing baseline. Further, little or no performance drop is observed when replacing half of the input-dependent attention matrices with constant (input-independent) ones. Interestingly, we show that better-performing models lose more from applying our method than weaker models, suggesting that the utilization of the input-dependent attention mechanism might be a factor in their success. Our results motivate research on simpler alternatives to input-dependent attention, as well as on methods for better utilization of this mechanism in the Transformer architecture.

从有限的资源中获得最大收益可以进步自然语言处理（NLP）研究和实践，同时保守资源。这些资源可能是数据，时间，存储或能源。NLP的最新工作从缩放率产生了有趣的结果。但是，仅使用比例来改善结果意味着资源消耗也会扩展。这种关系激发了对有效方法的研究，这些方法需要更少的资源才能获得相似的结果。这项调查涉及NLP效率的方法和发现，旨在指导该领域的新研究人员并激发新方法的发展。

虽然视觉和语言模型在视觉问题回答等任务上表现良好，但在基本的人类常识性推理技能方面，它们会挣扎。在这项工作中，我们介绍了Winogavil：在线游戏，以收集视觉和语言协会（例如，狼人到满月），用作评估最先进模型的动态基准。受欢迎的纸牌游戏代号的启发，Spymaster提供了与几个视觉候选者相关的文本提示，另一个玩家必须识别它们。人类玩家因创建对竞争对手AI模型而具有挑战性的联想而获得了回报，但仍然可以由其他人类玩家解决。我们使用游戏来收集3.5k实例，发现它们对人类的直观（> 90％的Jaccard索引），但对最先进的AI模型充满挑战，其中最佳模型（Vilt）的得分为52％ ，成功的位置在视觉上是显着的。我们的分析以及我们从玩家那里收集的反馈表明，收集的关联需要多种推理技能，包括一般知识，常识，抽象等。我们发布数据集，代码和交互式游戏，旨在允许未来的数据收集，可用于开发具有更好关联能力的模型。

我们介绍了一种零拍的视频字幕方法，该方法采用了两个冷冻网络：GPT-2语言模型和剪辑图像文本匹配模型。匹配分数用于引导语言模型生成一个句子，该句子的平均匹配分数高于视频帧的一个子集。与零拍图像字幕方法不同，我们的工作立即考虑整个句子。这是通过在生成过程中优化从头开始的一部分，通过在提示中修改所有其他令牌的表示，并通过迭代重复该过程，逐渐提高生成句子的特殊性和全面性来实现。我们的实验表明，生成的字幕是连贯的，并显示了广泛的现实知识。我们的代码可在以下网址找到：https：//github.com/yoadtew/zero-shot-video-to-text

预期模型的大小正在增加，它们在各种NLP任务上的性能也在增加。但是，随着记忆能力的增长，他们可能会增加更多的社会偏见。在这项工作中，我们检查了模型大小及其性别偏见之间的联系（特别是职业性别偏见）。我们在两个设置中测量三个蒙版语言模型家族（Roberta，Deberta和T5）中的偏见：直接使用基于提示的方法，并使用下游任务（Winogender）。一方面，我们发现较大的模型在以前的任务上获得了更高的偏差分数，但是当对后者进行评估时，它们会造成更少的性别错误。为了检查这些潜在的矛盾结果，我们仔细研究了Winogender不同模型的行为。我们发现，尽管较大的模型的表现要比较小的模型，但其错误是由性别偏见引起的概率。此外，我们发现，与抗疾病的型号相比，刻板印象误差的比例随模型大小而生长。我们的发现突出了增加模型大小可能引起的潜在风险。

通过提供前所未有的计算资源访问，云计算能够在机器学习等技术中快速增长，其计算需求产生了高能源成本和相应的碳足迹。结果，最近的奖学金呼吁更好地估计AI的温室气体影响：当今的数据科学家无法轻松或可靠地访问该信息的测量，从而排除了可行策略的发展。向用户提供有关软件碳强度的信息的云提供商是一种基本的垫脚石，以最大程度地减少排放。在本文中，我们提供了一个测量软件碳强度的框架，并建议通过使用每个能量单元使用基于位置和特定时间的边际排放数据来测量运行碳排放。我们为一组自然语言处理和计算机视觉的现代模型提供了操作软件强度的测量，以及各种模型尺寸，包括预处理61亿个参数语言模型。然后，我们评估了一套用于减少Microsoft Azure Cloud Compute平台排放的方法套件：使用不同地理区域中的云实例，在一天中的不同时间使用云实例，并在边际碳强度高于某个阈值时动态暂停云实例。我们证实了先前的结果，即数据中心的地理区域在给定云实例的碳强度中起着重要作用，并发现选择合适的区域可能具有最大的运营排放减少影响。我们还表明，一天中的时间对操作软件碳强度有显着影响。最后，我们最终提出了有关机器学习从业人员如何使用软件碳强度信息来减少环境影响的建议。

Large-scale datasets for natural language inference are created by presenting crowd workers with a sentence (premise), and asking them to generate three new sentences (hypotheses) that it entails, contradicts, or is logically neutral with respect to. We show that, in a significant portion of such data, this protocol leaves clues that make it possible to identify the label by looking only at the hypothesis, without observing the premise. Specifically, we show that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI (Bowman et al., 2015) and 53% of MultiNLI (Williams et al., 2018). Our analysis reveals that specific linguistic phenomena such as negation and vagueness are highly correlated with certain inference classes. Our findings suggest that the success of natural language inference models to date has been overestimated, and that the task remains a hard open problem.

Unsupervised learning-based anomaly detection in latent space has gained importance since discriminating anomalies from normal data becomes difficult in high-dimensional space. Both density estimation and distance-based methods to detect anomalies in latent space have been explored in the past. These methods prove that retaining valuable properties of input data in latent space helps in the better reconstruction of test data. Moreover, real-world sensor data is skewed and non-Gaussian in nature, making mean-based estimators unreliable for skewed data. Again, anomaly detection methods based on reconstruction error rely on Euclidean distance, which does not consider useful correlation information in the feature space and also fails to accurately reconstruct the data when it deviates from the training distribution. In this work, we address the limitations of reconstruction error-based autoencoders and propose a kernelized autoencoder that leverages a robust form of Mahalanobis distance (MD) to measure latent dimension correlation to effectively detect both near and far anomalies. This hybrid loss is aided by the principle of maximizing the mutual information gain between the latent dimension and the high-dimensional prior data space by maximizing the entropy of the latent space while preserving useful correlation information of the original data in the low-dimensional latent space. The multi-objective function has two goals -- it measures correlation information in the latent feature space in the form of robust MD distance and simultaneously tries to preserve useful correlation information from the original data space in the latent space by maximizing mutual information between the prior and latent space.

The usage of technologically advanced devices has seen a boom in many domains, including education, automation, and healthcare; with most of the services requiring Internet connectivity. To secure a network, device identification plays key role. In this paper, a device fingerprinting (DFP) model, which is able to distinguish between Internet of Things (IoT) and non-IoT devices, as well as uniquely identify individual devices, has been proposed. Four statistical features have been extracted from the consecutive five device-originated packets, to generate individual device fingerprints. The method has been evaluated using the Random Forest (RF) classifier and different datasets. Experimental results have shown that the proposed method achieves up to 99.8% accuracy in distinguishing between IoT and non-IoT devices and over 97.6% in classifying individual devices. These signify that the proposed method is useful in assisting operators in making their networks more secure and robust to security breaches and unauthorized access.