Tag
This paper explores interpretable Natural Language Inference (NLI) using graph-based representations of atomic propositions, introducing a pipeline that achieves 89.7% accuracy on SNLI with a trade-off in performance for interpretability.
This paper proposes representing multimodal data (image, video, text) as bags of atomic propositions (e.g., 'person holding cup'), unified via a global semantic codebook, enabling interpretable, compositional, and cross-modal understanding. The framework is demonstrated on autonomous driving and open-world data.