# Prediction or Comparison: Toward Interpretable Qualitative Reasoning

arXiv: https://arxiv.org/abs/2106.02399 · HTML: https://mlsanity.com/paper/2106.02399/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Learning to Reason: End-to-End Module Networks for Visual Question Answering](https://mlsanity.com/paper/1704.05526/) (2017)
- [QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions](https://mlsanity.com/paper/1909.03553/) (2019)
- [Reasoning Over Paragraph Effects in Situations](https://mlsanity.com/paper/1908.05852/) (2019)
- [Logic-Guided Data Augmentation and Regularization for Consistent Question Answering](https://mlsanity.com/paper/2004.10157/) (2020)
- [Neural Module Networks for Reasoning over Text](https://mlsanity.com/paper/1912.04971/) (2019)
- [QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships](https://mlsanity.com/paper/1811.08048/) (2018)
- [Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning](https://mlsanity.com/paper/1909.05803/) (2019)
- [Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension](https://mlsanity.com/paper/1906.05210/) (2019)
- [Neural Compositional Denotational Semantics for Question Answering](https://mlsanity.com/paper/1808.09942/) (2018)
- [Multi-Step Inference for Reasoning Over Paragraphs](https://mlsanity.com/paper/2004.02995/) (2020)
- [Towards Interpretable Reasoning over Paragraph Effects in Situation](https://mlsanity.com/paper/2010.01272/) (2020)
- [A Generate-Validate Approach to Answering Questions about Qualitative Relationships](https://mlsanity.com/paper/1908.03645/) (2019)

## Abstract (arXiv)

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.