ACL Findings2021
Prediction or Comparison: Toward Interpretable Qualitative Reasoning
Mucheng Ren, Heyan Huang, Yang Gao
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on2
Related papers
- Towards Interpretable Reasoning over Paragraph Effects in SituationMucheng Ren, Xiubo Geng, Tao Qin, Heyan Huang et al.EMNLP 2020 · 6 citations
- Neural Natural Logic Inference for Interpretable Question AnsweringJihao Shi, Xiao Ding, Li Du, Ting Liu et al.EMNLP 2021 · 10 citations
- Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"Saeed Amizadeh, Hamid Palangi, Alex Polozov, Yichen Huang et al.ICML 2020 · 74 citations
- Explicit Knowledge Incorporation for Visual ReasoningYifeng Zhang, Ming Jiang, Qi ZhaoCVPR 2021
- An Explicitly Relational Neural Network ArchitectureMurray Shanahan, Kyriacos Nikiforou, Antonia Creswell, Christos Kaplanis et al.ICML 2020 · 72 citations
