Numbers Matter! Bringing Quantity-awareness to Retrieval Systems

TL;DR

This paper introduces quantity-aware ranking techniques that incorporate numerical and unit information into retrieval systems to improve search relevance for queries involving quantities, supported by new benchmarks in finance and medicine.

Contribution

The paper proposes novel quantity-aware ranking methods and creates benchmark datasets to evaluate their effectiveness in handling numerical queries.

Findings

Quantitative information improves retrieval relevance.

Proposed models outperform lexical and neural baselines.

New benchmarks facilitate future research in quantity-aware retrieval.

Abstract

Quantitative information plays a crucial role in understanding and interpreting the content of documents. Many user queries contain quantities and cannot be resolved without understanding their semantics, e.g., ``car that costs less than $10k''. Yet, modern search engines apply the same ranking mechanisms for both words and quantities, overlooking magnitude and unit information. In this paper, we introduce two quantity-aware ranking techniques designed to rank both the quantity and textual content either jointly or independently. These techniques incorporate quantity information in available retrieval systems and can address queries with numerical conditions equal, greater than, and less than. To evaluate the effectiveness of our proposed models, we introduce two novel quantity-aware benchmark datasets in the domains of finance and medicine and compare our method against various lexical and neural models. The code and data are available under https://github.com/satya77/QuantityAwareRankers.