论文标题
对语言和知识图的嵌入空间对齐方法的调查
A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
论文作者
论文摘要
神经嵌入方法已成为计算机视觉，自然语言处理以及最近的图形分析领域的主食。鉴于这些算法的普遍性质，自然的问题变成了如何利用不同数据源的嵌入空间或对齐的嵌入。为此，我们调查了嵌入算法的单词，句子和知识图的当前研究格局。我们提供了相关对准技术的分类，并讨论在此研究领域中使用的基准数据集。通过将这些多样化的方法收集到一个单一的调查中，我们希望进一步激励研究各种数据类型和来源的嵌入空间的一致性。
Neural embedding approaches have become a staple in the fields of computer vision, natural language processing, and more recently, graph analytics. Given the pervasive nature of these algorithms, the natural question becomes how to exploit the embedding spaces to map, or align, embeddings of different data sources. To this end, we survey the current research landscape on word, sentence and knowledge graph embedding algorithms. We provide a classification of the relevant alignment techniques and discuss benchmark datasets used in this field of research. By gathering these diverse approaches into a singular survey, we hope to further motivate research into alignment of embedding spaces of varied data types and sources.
