This survey documents representation approaches for classification across different modalities, from purely content-based methods to techniques utilizing external sources of structured knowledge. We present studies related to three paradigms used for representation, namely (a) low-level template-matching methods, (b) aggregation-based approaches, and (c) deep representation learning systems. We then describe existing resources of structure knowledge and elaborate on the need for enriching representations with such information. Approaches that utilize knowledge resources are presented next, organized with respect to how external information is exploited, i.e., (a) input enrichment and modification, (b) knowledge-based refinement and (c) end-to-end knowledge-aware systems. We subsequently provide a high-level discussion to summarize and compare strengths/weaknesses of the representation/enrichment paradigms proposed, and conclude the survey with an overview of relevant research findings and possible directions for future work.

这项调查记录了跨不同模式的分类表示方法，从纯粹基于内容的方法到利用外部结构化知识源的技术。我们提出了与用于表示的三种范式相关的研究，即（a）低级模板匹配方法，（b）基于聚合的方法，以及（c）深度表示学习系统。然后，我们描述现有的结构知识资源，并详细说明用这些信息丰富表示的需要。接下来介绍利用知识资源的方法，根据如何利用外部信息进行组织，即（a）输入丰富和修改，（b）基于知识的细化和（c）端到端知识感知系统。