CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics
This work addresses the challenge of accurately encoding numerical and structured data semantics for large pre-trained models, which is a problem for anyone working with numerical reasoning tasks.
This paper introduces CONE, a hybrid transformer encoder pre-trained model designed to embed numbers, ranges, and Gaussians while preserving distance. It achieves an F1 score of 87.28% on DROP, an improvement of up to 9.37% in F1 over SOTA baselines, and a Recall@10 gain of up to 25%.
Large pre-trained models (LMs) and Large Language Models (LLMs) are typically effective at capturing language semantics and contextual relationships. However, these models encounter challenges in maintaining optimal performance on tasks involving numbers. Blindly treating numerical or structured data as terms is inadequate -- their semantics must be well understood and encoded by the models. In this paper, we propose CONE, a hybrid transformer encoder pre-trained model that encodes numbers, ranges, and gaussians into an embedding vector space preserving distance. We introduce a novel composite embedding construction algorithm that integrates numerical values, ranges or gaussians together with their associated units and attribute names to precisely capture their intricate semantics. We conduct extensive experimental evaluation on large-scale datasets across diverse domains (web, medical, finance, and government) that justifies CONE's strong numerical reasoning capabilities, achieving an F1 score of 87.28% on DROP, a remarkable improvement of up to 9.37% in F1 over state-of-the-art (SOTA) baselines, and outperforming major SOTA models with a significant Recall@10 gain of up to 25%.