Zero-shot relation triplet extraction (ZeroRTE) aims to extract relation triplets from unstructured texts under the zero-shot setting, where the relation sets at the training and testing stages are disjoint. Previous state-of-the-art method handles this challenging task by leveraging pretrained language models to generate data as additional training samples, which increases the training cost and severely constrains the model performance. To address the above issues, we propose a novel method named PCRED for ZeroRTE with Potential Candidate Relation Selection and Entity Boundary Detection. The remarkable characteristic of PCRED is that it does not rely on additional data and still achieves promising performance. The model adopts a relation-first paradigm, recognizing unseen relations through candidate relation selection. With this approach, the semantics of relations are naturally infused in the context. Entities are extracted based on the context and the semantics of relations subsequently. We evaluate our model on two ZeroRTE datasets. The experiment results show that our method consistently outperforms previous works. Our code will be available at https://anonymous.4open.science/r/PCRED.
translated by 谷歌翻译
In this work, we identify elements of effective machine learning datasets in astronomy and present suggestions for their design and creation. Machine learning has become an increasingly important tool for analyzing and understanding the large-scale flood of data in astronomy. To take advantage of these tools, datasets are required for training and testing. However, building machine learning datasets for astronomy can be challenging. Astronomical data is collected from instruments built to explore science questions in a traditional fashion rather than to conduct machine learning. Thus, it is often the case that raw data, or even downstream processed data is not in a form amenable to machine learning. We explore the construction of machine learning datasets and we ask: what elements define effective machine learning datasets? We define effective machine learning datasets in astronomy to be formed with well-defined data points, structure, and metadata. We discuss why these elements are important for astronomical applications and ways to put them in practice. We posit that these qualities not only make the data suitable for machine learning, they also help to foster usable, reusable, and replicable science practices.
translated by 谷歌翻译
人类智能能够首先学习一些基本技能,以解决基本问题,然后将这种基本技能融合到解决复杂或新问题的复杂技能中。例如,基本技能``挖洞'',``放树,'''``回填''和``浇水'''构成复杂的技能``植物''。此外,可以重复使用一些基本技能来解决其他问题。例如,基本技能``挖洞''不仅可以用于种植树木,而且还可以用于采矿,建造排水管或垃圾填埋场。学习基本技能并重复使用各种任务的能力对人类非常重要,因为它有助于避免学习太多的技能来解决每个任务,并可以通过仅学习几个数量来解决组成数量的任务数量基本技能,可以节省人脑中大量的记忆和计算。我们认为,机器智能还应捕捉学习基本技能并通过构成复杂技能的能力。在计算机科学语言中,每种基本技能都是“模块”,它是一个可重复使用的具体含义的网络,并执行特定的基本操作。将模块组装成更大的``模型'',以完成更复杂的任务。组装过程适应输入或任务,即,对于给定的任务,应该将模块组装成解决任务的最合适的模型中。结果,不同的输入或任务可能具有不同的组装模型,从而实现自组装AI。在这项工作中,我们提出了模块化的自适应神经体系结构搜索(MANAS),以演示上述想法。不同数据集上的实验表明,MANAS组装的自适应体系结构优于静态全局体系结构。进一步的实验和经验分析为魔力的有效性提供了见解。
translated by 谷歌翻译
图表可以表示实体之间的关系信息,图形结构广泛用于许多智能任务,例如搜索,推荐和问题应答。然而,实际上大多数图形结构数据都遭受了不完整性,因此链路预测成为一个重要的研究问题。虽然提出了许多模型来用于链路预测,但以下两个问题仍然仍然较少:(1)大多数方法在不利用相关链路中使用丰富的信息,大多数方法都独立模型,并且(2)现有型号主要基于关联设计学习并没有考虑推理。通过这些问题,在本文中,我们提出了图表协作推理(GCR),它可以使用邻居与逻辑推理视角的关系中的关系推理。我们提供了一种简单的方法来将图形结构转换为逻辑表达式,以便链路预测任务可以转换为神经逻辑推理问题。我们应用逻辑受限的神经模块根据逻辑表达式构建网络架构,并使用反向传播以有效地学习模型参数,这在统一架构中桥接可分辨率的学习和象征性推理。为了展示我们工作的有效性,我们对图形相关任务进行实验,例如基于常用的基准数据集的链路预测和推荐,我们的图表合作推理方法实现了最先进的性能。
translated by 谷歌翻译
由于越来越多的用户使用它们来寻求和决策,推荐制度对人类和社会的影响增加了对人类和社会的影响。因此,在建议中解决潜在的不公平问题至关重要。就像用户在物品上具有个性化的偏好,用户对公平性的要求也是个性化的许多情况。因此,为用户提供个性化的公平建议,以满足其个性化的公平需求。此外,以前的公平建议作品主要关注基于关联的公平性。但是,重要的是从联合公平概念前进,以便在推荐系统中更适当地评估公平性的因果公平概念。本文根据上述考虑,侧重于为推荐系统中的用户实现个性化的反事实公平。为此,我们介绍了一个框架,通过对建议产生特征 - 独立的用户嵌入来实现通过对抗学习来实现反转公平的建议。该框架允许推荐系统为用户实现个性化的公平,同时也涵盖非个性化情况。在浅层和深刻的推荐算法上的两个现实数据集的实验表明,我们的方法可以为具有理想的推荐性能的用户生成更公平的建议。
translated by 谷歌翻译
Near infrared (NIR) to Visible (VIS) face matching is challenging due to the significant domain gaps as well as a lack of sufficient data for cross-modality model training. To overcome this problem, we propose a novel method for paired NIR-VIS facial image generation. Specifically, we reconstruct 3D face shape and reflectance from a large 2D facial dataset and introduce a novel method of transforming the VIS reflectance to NIR reflectance. We then use a physically-based renderer to generate a vast, high-resolution and photorealistic dataset consisting of various poses and identities in the NIR and VIS spectra. Moreover, to facilitate the identity feature learning, we propose an IDentity-based Maximum Mean Discrepancy (ID-MMD) loss, which not only reduces the modality gap between NIR and VIS images at the domain level but encourages the network to focus on the identity features instead of facial details, such as poses and accessories. Extensive experiments conducted on four challenging NIR-VIS face recognition benchmarks demonstrate that the proposed method can achieve comparable performance with the state-of-the-art (SOTA) methods without requiring any existing NIR-VIS face recognition datasets. With slightly fine-tuning on the target NIR-VIS face recognition datasets, our method can significantly surpass the SOTA performance. Code and pretrained models are released under the insightface (https://github.com/deepinsight/insightface/tree/master/recognition).
translated by 谷歌翻译
现有的基于视频的人重新识别(REID)的方法主要通过功能提取器和功能聚合器来了解给定行人的外观特征。但是,当不同的行人外观相似时,外观模型将失败。考虑到不同的行人具有不同的步行姿势和身体比例,我们建议学习视频检索的外观功能之外的歧视性姿势功能。具体而言,我们实现了一个两分支的体系结构,以单独学习外观功能和姿势功能,然后将它们串联在一起进行推理。为了学习姿势特征,我们首先通过现成的姿势检测器检测到每个框架中的行人姿势,并使用姿势序列构建时间图。然后,我们利用复发图卷积网络(RGCN)来学习时间姿势图的节点嵌入,该姿势图设计了一种全局信息传播机制,以同时实现框内节点的邻域聚集,并在框架间图之间传递消息。最后,我们提出了一种由节点注意和时间注意的双重意见方法,以从节点嵌入中获得时间图表示,其中采用自我注意机制来了解每个节点和每个帧的重要性。我们在三个基于视频的REID数据集(即火星,Dukemtmc和Ilids-Vid)上验证了所提出的方法,其实验结果表明,学习的姿势功能可以有效地改善现有外观模型的性能。
translated by 谷歌翻译
基于模型的步态识别方法通常采用行人步行姿势来识别人类。但是,由于摄像头视图的改变,现有方法并未明确解决人类姿势的较大阶层差异。在本文中,我们建议通过通过低UPPER生成的对抗网络(Lugan)学习全级转换矩阵来为每个单视姿势样本生成多视图姿势序列。通过摄像机成像的先验,我们得出的是,跨视图之间的空间坐标满足了全级矩阵的线性转换,因此,本文采用了对抗性训练来从源姿势学习转换矩阵,并获得目标视图以获得目标。目标姿势序列。为此,我们实现了由图形卷积(GCN)层组成的发电机,完全连接(FC)层和两支分支卷积(CNN)层:GCN层和FC层编码源姿势序列和目标视图,然后是CNN分支最后,分别学习一个三角形基质和上三角基质,最后它们被乘以制定全级转换矩阵。出于对抗训练的目的,我们进一步设计了一个条件鉴别因子,该条件区分姿势序列是真实的还是产生的。为了启用高级相关性学习,我们提出了一个名为Multi尺度超图卷积(HGC)的插件播放模块,以替换基线中的空间图卷积层,该层可以同时模拟联合级别的部分,部分部分 - 水平和身体水平的相关性。在两个大型步态识别数据集(即CASIA-B和OUMVLP置位)上进行的广泛实验表明,我们的方法的表现优于基线模型,并以一个较大的边距基于基于姿势的方法。
translated by 谷歌翻译
ROUGE is a standard automatic evaluation metric based on n-grams for sequence-to-sequence tasks, while cross-entropy loss is an essential objective of neural network language model that optimizes at a unigram level. We present differentiable n-gram objectives, attempting to alleviate the discrepancy between training criterion and evaluating criterion. The objective maximizes the probabilistic weight of matched sub-sequences, and the novelty of our work is the objective weights the matched sub-sequences equally and does not ceil the number of matched sub-sequences by the ground truth count of n-grams in reference sequence. We jointly optimize cross-entropy loss and the proposed objective, providing decent ROUGE score enhancement over abstractive summarization dataset CNN/DM and XSum, outperforming alternative n-gram objectives.
translated by 谷歌翻译
可见红外人重新识别(VI-REID)由于可见和红外模式之间存在较大的差异而受到挑战。大多数开创性方法通过学习模态共享和ID相关的功能来降低类内变型和跨性间差异。但是,在VI-REID中尚未充分利用一个显式模态共享提示。此外,现有特征学习范例在全局特征或分区特征条带上强加约束,忽略了全局和零件特征的预测一致性。为了解决上述问题,我们将构成估算作为辅助学习任务,以帮助vi-reid任务在端到端的框架中。通过以互利的方式联合培训这两个任务,我们的模型学习了更高质量的模态共享和ID相关的功能。在它之上,通过分层特征约束(HFC)无缝同步全局功能和本地特征的学习,前者使用知识蒸馏策略监督后者。两个基准VI-REID数据集的实验结果表明,该方法始终如一地通过显着的利润来改善最先进的方法。具体而言,我们的方法在RegDB数据集上取决于针对最先进的方法的近20美元\%$地图改进。我们的兴趣调查结果突出了vi-reid中辅助任务学习的使用。
translated by 谷歌翻译