在本文中，我们介绍了TweetNLP，这是社交媒体中自然语言处理（NLP）的集成平台。TweetNLP支持一套多样化的NLP任务，包括诸如情感分析和命名实体识别的通用重点领域，以及社交媒体特定的任务，例如表情符号预测和进攻性语言识别。特定于任务的系统由专门用于社交媒体文本的合理大小的基于变压器的语言模型（尤其是Twitter）提供动力，无需专用硬件或云服务即可运行。TweetNLP的主要贡献是：（1）使用适合社会领域的各种特定于任务的模型，用于支持社交媒体分析的现代工具包的集成python库；（2）使用我们的模型进行无编码实验的交互式在线演示；（3）涵盖各种典型社交媒体应用的教程。

We outline our work on evaluating robots that assist older adults by engaging with them through multiple modalities that include physical interaction. Our thesis is that to increase the effectiveness of assistive robots: 1) robots need to understand and effect multimodal actions, 2) robots should not only react to the human, they need to take the initiative and lead the task when it is necessary. We start by briefly introducing our proposed framework for multimodal interaction and then describe two different experiments with the actual robots. In the first experiment, a Baxter robot helps a human find and locate an object using the Multimodal Interaction Manager (MIM) framework. In the second experiment, a NAO robot is used in the same task, however, the roles of the robot and the human are reversed. We discuss the evaluation methods that were used in these experiments, including different metrics employed to characterize the performance of the robot in each case. We conclude by providing our perspective on the challenges and opportunities for the evaluation of assistive robots for older adults in realistic settings.

The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning techniques in the industry. Neural Architecture Search (NAS) exploits deep learning techniques to autonomously produce neural network architectures whose results rival the state-of-the-art models hand-crafted by AI experts. However, this approach requires significant computational resources and hardware investments, making it less appealing for real-usage applications. This article presents the third version of Pareto-Optimal Progressive Neural Architecture Search (POPNASv3), a new sequential model-based optimization NAS algorithm targeting different hardware environments and multiple classification tasks. Our method is able to find competitive architectures within large search spaces, while keeping a flexible structure and data processing pipeline to adapt to different tasks. The algorithm employs Pareto optimality to reduce the number of architectures sampled during the search, drastically improving the time efficiency without loss in accuracy. The experiments performed on images and time series classification datasets provide evidence that POPNASv3 can explore a large set of assorted operators and converge to optimal architectures suited for the type of data provided under different scenarios.

Quantifying the perceptual similarity of two images is a long-standing problem in low-level computer vision. The natural image domain commonly relies on supervised learning, e.g., a pre-trained VGG, to obtain a latent representation. However, due to domain shift, pre-trained models from the natural image domain might not apply to other image domains, such as medical imaging. Notably, in medical imaging, evaluating the perceptual similarity is exclusively performed by specialists trained extensively in diverse medical fields. Thus, medical imaging remains devoid of task-specific, objective perceptual measures. This work answers the question: Is it necessary to rely on supervised learning to obtain an effective representation that could measure perceptual similarity, or is self-supervision sufficient? To understand whether recent contrastive self-supervised representation (CSR) may come to the rescue, we start with natural images and systematically evaluate CSR as a metric across numerous contemporary architectures and tasks and compare them with existing methods. We find that in the natural image domain, CSR behaves on par with the supervised one on several perceptual tests as a metric, and in the medical domain, CSR better quantifies perceptual similarity concerning the experts' ratings. We also demonstrate that CSR can significantly improve image quality in two image synthesis tasks. Finally, our extensive results suggest that perceptuality is an emergent property of CSR, which can be adapted to many image domains without requiring annotations.

In this paper we propose new probabilistic and dynamic (adaptive) strategies to create multi-method ensembles based on the Coral Reefs Optimization with Substrate Layers (CRO-SL) algorithm. The CRO-SL is an evolutionary-based ensemble approach, able to combine different search procedures within a single population. In this work we discuss two different probabilistic strategies to improve the algorithm. First, we defined the Probabilistic CRO-SL (PCRO-SL), which substitutes the substrates in the CRO-SL population by {\em tags} associated with each individual. Each tag represents a different operator which will modify the individual in the reproduction phase. In each generation of the algorithm, the tags are randomly assigned to the individuals with a similar probability, obtaining this way an ensemble with a more intense change in the application of different operators to a given individual than the original CRO-SL. The second strategy discussed in this paper is the Dynamical Probabilistic CRO-SL (DPCRO-SL), in which the probability of tag assignment is modified during the evolution of the algorithm, depending on the quality of the solutions generated in each substrate. Thus, the best substrates in the search process will be assigned with a higher probability that those which showed a worse performance during the search. We test the performance of the proposed probabilistic and dynamic ensembles in different optimization problems, including benchmark functions and a real application of wind turbines layout optimization, comparing the results obtained with that of existing algorithms in the literature.

如今，深度学习模型的所有者和开发人员必须考虑其培训数据的严格隐私保护规则，通常是人群来源且保留敏感信息。如今，深入学习模型执行隐私保证的最广泛采用的方法依赖于实施差异隐私的优化技术。根据文献，这种方法已被证明是针对多种模型的隐私攻击的成功防御，但其缺点是对模型的性能的实质性降级。在这项工作中，我们比较了差异私有的随机梯度下降（DP-SGD）算法与使用正则化技术的标准优化实践的有效性。我们分析了生成模型的实用程序，培训性能以及成员推理和模型反转攻击对学习模型的有效性。最后，我们讨论了差异隐私的缺陷和限制，并从经验上证明了辍学和L2型规范的卓越保护特性。

我们为通过连续时间（非策略）梯度下降而训练的分类器建立了一个崩解的Pac-bayesian结合。与Pac-Bayesian环境中的标准配置相反，我们的结果适用于确定性的培训算法，以随机初始化为条件，而无需任何$ \ textit {de-randomisation} $ step。我们对我们提出的界限的主要特征进行了广泛的讨论，并在分析和经验上研究了它在线性模型上的行为，从而找到了有希望的结果。

参考分辨率旨在识别说话者所引用的实体，在现实世界中更为复杂：新的指称者可以由代理商参与和/或仅仅因为属于共享的物理设置而创建和/或显着。我们的重点是在多模式对话中解决对大屏幕显示上的可视化的引用；至关重要的是，参考分辨率直接参与创建新的可视化的过程。我们描述了通过语言和手势以及新实体建立在大屏幕上出现的可视化的用户引用的注释，这是由于执行用户请求创建新可视化而产生的。我们还描述了我们的参考分辨率管道，该管道依赖于信息状态体系结构来维护对话环境。我们报告有关检测和解决参考文献的结果，模型上下文信息的有效性以及创建可视化的请求不足。我们还尝试了常规的CRF和深度学习 /变压器模型（Bilstm-CRF和Bert-CRF），以在用户话语文本中标记参考。我们的结果表明，尽管CRF仍然表现出色，但转移学习显着提高了深度学习方法的性能，这表明传统方法可能会更好地概括为低资源数据。

问答系统被认为是流行且经常有效的信息在网络上寻求信息的手段。在这样的系统中，寻求信息者可以通过自然语言提出问题来获得对他们的查询的简短回应。交互式问题回答是一种最近提出且日益流行的解决方案，它位于问答和对话系统的交集。一方面，用户可以以普通语言提出问题，并找到对她的询问的实际回答；另一方面，如果在初始请求中有多个可能的答复，很少或歧义，则系统可以将问题交通会话延长到对话中。通过允许用户提出更多问题，交互式问题回答使用户能够与系统动态互动并获得更精确的结果。这项调查提供了有关当前文献中普遍存在的交互式提问方法的详细概述。它首先要解释提问系统的基本原理，从而定义新的符号和分类法，以将所有已确定的作品结合在统一框架内。然后，根据提出的方法，评估方法和数据集/应用程序域来介绍和检查有关交互式问题解答系统的审查已发表的工作。我们还描述了围绕社区提出的特定任务和问题的趋势，从而阐明了学者的未来利益。 GitHub页面的综合综合了本文献研究中涵盖的所有主要主题，我们的工作得到了进一步的支持。 https://sisinflab.github.io/interactive-question-answering-systems-survey/

软气动执行器已经在许多软机器人系统中看到了应用，其压力驱动的性质提出了控制其运动的独特挑战和机会。在这项工作中，我们提出了一个新概念：通过末端几何形状设计和控制气动执行器。我们演示了一个新颖的执行器类，称为折叠气动人造肌肉（Foldpam），该肌肉具有一个薄纤维的空气袋，两侧对称折叠。改变执行器的折叠部分会改变最终约束，从而改变力 - 应变关系。我们通过测量具有各种长度和折叠量的单个foldpam单元的力 - 应变关系来实验研究这一变化。除静态几何单元外，驱动的FOLDPAM设备还设计为产生末端几何形状的连续，按需调整，从而实现闭环位置控制，同时保持恒定压力。使用设备的实验表明几何控制允许进入力 - 应变平面上的不同区域，并且闭环几何控制可以在驱动范围的0.5％以内实现误差。