Prediction or Comparison: Toward Interpretable Qualitative Reasoning

TL;DR

This paper introduces neural network modules for qualitative reasoning tasks that enable both prediction and comparison, providing interpretable intermediate outputs and demonstrating effectiveness on QA datasets.

Contribution

It proposes a unified neural approach for qualitative reasoning that enhances interpretability and generalization across different reasoning tasks.

Findings

Effective performance on QuaRTz and QuaRel datasets

Modules produce interpretable intermediate reasoning steps

Method generalizes well to different qualitative reasoning tasks

Abstract

Qualitative relationships illustrate how changing one property (e.g., moving velocity) affects another (e.g., kinetic energy) and constitutes a considerable portion of textual knowledge. Current approaches use either semantic parsers to transform natural language inputs into logical expressions or a "black-box" model to solve them in one step. The former has a limited application range, while the latter lacks interpretability. In this work, we categorize qualitative reasoning tasks into two types: prediction and comparison. In particular, we adopt neural network modules trained in an end-to-end manner to simulate the two reasoning processes. Experiments on two qualitative reasoning question answering datasets, QuaRTz and QuaRel, show our methods' effectiveness and generalization capability, and the intermediate outputs provided by the modules make the reasoning process interpretable.