论文标题
通过常识性知识改善零射击学习基准
Improving Zero Shot Learning Baselines with Commonsense Knowledge
论文作者
论文摘要
零射击学习 - 完全不相交的课程训练和测试的问题 - 在很大程度上取决于其从火车课上转移知识的能力。传统上由人类定义属性（HA）或分布式单词嵌入（DWE）组成的语义嵌入，用于通过改善视觉和语义嵌入之间的关联来促进这种转移。在本文中，我们利用概念网中定义的节点之间的明确关系（常识性知识图）通过使用基于图卷积网络的自动编码器来生成类标签的常识性嵌入。当我们将常识嵌入与现有的语义嵌入（即HA和DWE）融合时，我们在三个标准基准数据集上进行的实验超过了强基础。
Zero shot learning -- the problem of training and testing on a completely disjoint set of classes -- relies greatly on its ability to transfer knowledge from train classes to test classes. Traditionally semantic embeddings consisting of human defined attributes (HA) or distributed word embeddings (DWE) are used to facilitate this transfer by improving the association between visual and semantic embeddings. In this paper, we take advantage of explicit relations between nodes defined in ConceptNet, a commonsense knowledge graph, to generate commonsense embeddings of the class labels by using a graph convolution network-based autoencoder. Our experiments performed on three standard benchmark datasets surpass the strong baselines when we fuse our commonsense embeddings with existing semantic embeddings i.e. HA and DWE.
