论文标题
“如果...”程序推理的相关常识子图
Relevant CommonSense Subgraphs for "What if..." Procedural Reasoning
论文作者
论文摘要
我们研究了学习因果推理对程序文本的挑战，以回答“如果...”何时需要外常识知识。我们向1）提出了一种新型的多跳图推理模型。 2）通过推理从常识子图获得的表示以及问题与上下文之间的上下文相互作用来预测因果答案。我们评估了WIQA基准测试的模型，并与最近的模型相比实现了最先进的性能。
We study the challenge of learning causal reasoning over procedural text to answer "What if..." questions when external commonsense knowledge is required. We propose a novel multi-hop graph reasoning model to 1) efficiently extract a commonsense subgraph with the most relevant information from a large knowledge graph; 2) predict the causal answer by reasoning over the representations obtained from the commonsense subgraph and the contextual interactions between the questions and context. We evaluate our model on WIQA benchmark and achieve state-of-the-art performance compared to the recent models.
