Parallax: Visualizing And Understanding The Semantics Of Embedding Spaces Via Algebraic Formulae

Embeddings are a fundamental component of many modern machine learning and natural language processing models. Understanding them and visualizing them is essential for gathering insights about the information they capture and the behavior of the models. In this paper, we introduce Parallax(1), a tool explicitly designed for this task. Parallax allows the user to use both state-of-the-art embedding analysis methods (PCA and t-SNE) and a simple yet effective task-oriented approach where users can explicitly define the axes of the projection through algebraic formulae. In this approach, embeddings are projected into a semantically meaningful subspace, which enhances interpretability and allows for more fine-grained analysis. We demonstrate(2) the power of the tool and the proposed methodology through a series of case studies and a user study.