Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful knowledge to reason over. To address these issues, we propose a new KG-augmented model: Hybrid Graph Network (HGN). Unlike prior methods, HGN learns to jointly contextualize extracted and generated knowledge by reasoning over both within a unified graph structure. Given the task input context and an extracted KG subgraph, HGN is trained to generate embeddings for the subgraph's missing edges to form a "hybrid" graph, then reason over the hybrid graph while filtering out context-irrelevant edges. We demonstrate HGN's effectiveness through considerable performance gains across four commonsense reasoning benchmarks, plus a user study on edge validness and helpfulness.

翻译：最近,知识图表(KG)的扩充模型在各种常识推理任务方面取得了显著的成功,然而,KG边缘(事实)宽度和噪音边缘提取/生成往往阻碍模型获得有用的知识,从而无法理解。为了解决这些问题,我们提议了一个新的KG推荐模型:混合图表网络(HGN ) 。与以往的方法不同,HGN学会通过在统一图表结构内进行推理,将提取和生成的知识结合到一起。鉴于任务输入背景和提取的KG子集,HGN受过培训,为子集缺失的边缘生成嵌入“湿度”图,然后在过滤与环境有关的边缘时解释混合图。我们通过四个共同理论基准的显著绩效收益,加上关于边缘有效性和帮助性的用户研究,展示了HGN的实效。