Uncovering Meanings of Embeddings via Partial Orthogonality

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: embedding, representation, graphical models, partial orthogonality, Markov boundary
TL;DR: We generalize the notion of Markov boundary to embedding space using partial orthogonality to uncover semantic meanings
Abstract: Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure of such embeddings. Specifically, we look at a notion of "semantic independence" capturing the idea that, e.g., "eggplant" and "tomato" are independent given "vegetable". Although such examples are intuitive, it is difficult to formalize such a notion of semantic independence. The key observation here is that any sensible formalization should obey a set of so-called independence axioms, and thus any algebraic encoding of this structure should also obey these axioms. This leads us naturally to use partial orthogonality as the relevant algebraic structure. We develop theory and methods that allow us to demonstrate that partial orthogonality does indeed capture semantic independence. Complementary to this, we also introduce the concept of independence preserving embeddings where embeddings preserve the conditional independence structures of a distribution, and we prove the existence of such embeddings and approximations to them.
Submission Number: 9233