Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder

ArXi:2506.20083v4 Announce Type: replace Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language models (LMs). In this survey, we offer a novel perspective on latent space geometry through the lens of compositional semantics, a direction we refer to as \textit{semantic representation learning