Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
This work addresses the need for more efficient and interpretable commonsense reasoning systems in AI, though it is incremental as it builds on existing knowledge graph methods.
The authors tackled the problem of enhancing commonsense reasoning in pre-trained models by identifying that relation features, not node features, from commonsense knowledge graphs are key to performance improvement, and they designed a simple MLP-based encoder using statistical relation paths, achieving effectiveness across five benchmarks while reducing parameters.
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models~(PTMs) with a knowledge-aware graph neural network~(GNN) encoder that models a commonsense knowledge graph~(CSKG). Despite the effectiveness, these approaches are built on heavy architectures, and can't clearly explain how external knowledge resources improve the reasoning capacity of PTMs. Considering this issue, we conduct a deep empirical analysis, and find that it is indeed relation features from CSKGs (but not node features) that mainly contribute to the performance improvement of PTMs. Based on this finding, we design a simple MLP-based knowledge encoder that utilizes statistical relation paths as features. Extensive experiments conducted on five benchmarks demonstrate the effectiveness of our approach, which also largely reduces the parameters for encoding CSKGs. Our codes and data are publicly available at https://github.com/RUCAIBox/SAFE.