Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode compositional representations of the concepts over which they operate, such as correctly identifying ''red cube'' by reasoning over the constituents ''red'' and ''cube''. In this work, we focus on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way (e.g., differentiating ''cube behind sphere'' from ''sphere behind cube''). In order to inspect the performance of CLIP, we compare several architectures from research on compositional distributional semantics models (CDSMs), a line of research that attempts to implement traditional compositional linguistic structures within embedding spaces. We find that CLIP can compose concepts in a single-object setting, but in situations where concept binding is needed, performance drops dramatically. At the same time, CDSMs also perform poorly, with best performance at chance level.

翻译：近年来，结合文本与图像的大型神经网络模型取得了令人瞩目的进展。然而，这类模型在多大程度上能够编码其所处理概念的组合表征（例如通过推理构成要素“红色”和“立方体”来正确识别“红色立方体”），仍是一个未解之谜。本研究聚焦于大型预训练视觉语言模型（CLIP）在编码组合概念及以结构敏感方式绑定变量（例如区分“立方体位于球体后方”与“球体位于立方体后方”）方面的能力。为检验CLIP的性能，我们比较了 compositional 分布语义模型（CDSMs）研究领域的几种架构——该研究方向试图在嵌入空间中实现传统的组合语言结构。研究发现，CLIP可在单对象情境下组合概念，但在需要概念绑定的场景中，其性能急剧下降。与此同时，CDSMs的表现同样不佳，其最佳性能仅为随机水平。