Quantitative reasoning is a higher-order reasoning skill that any intelligent natural language understanding system can reasonably be expected to handle. We present EQUATE (Evaluating Quantitative Understanding Aptitude in Textual Entailment), a new framework for quantitative reasoning in textual entailment. We benchmark the performance of 9 published NLI models on EQUATE, and find that on average, state-of-the-art methods do not achieve an absolute improvement over a majority-class baseline, suggesting that they do not implicitly learn to reason with quantities. We establish a new baseline Q-REAS that manipulates quantities symbolically. In comparison to the best performing NLI model, it achieves success on numerical reasoning tests (+24.2%), but has limited verbal reasoning capabilities (-8.1%). We hope our evaluation framework will support the development of models of quantitative reasoning in language understanding.
@article{arxiv.1901.03735,
title = {EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference},
author = {Abhilasha Ravichander and Aakanksha Naik and Carolyn Rose and Eduard Hovy},
journal= {arXiv preprint arXiv:1901.03735},
year = {2019}
}