论文标题
知识感知问题回答的可扩展多跳的关系推理
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
论文作者
论文摘要
具有外部知识（例如，知识图）的增强问题答案（QA）模型的现有工作要么难以有效地对多跳跃关系建模，要么缺乏对模型预测理由的透明度。在本文中，我们提出了一种新颖的知识感知方法，该方法将预训练的语言模型（PTLMS）与多跳的关系推理模块（称为多跳图关系网络（MHGRN））相对。它对从外部知识图中提取的子图进行了多跳的，多关系推理。提出的推理模块统一了基于路径的推理方法和图形神经网络，以实现更好的解释性和可伸缩性。我们还从经验上展示了其对Consensensensensenseqa和OpenBookQA数据集的有效性和可扩展性，并通过案例研究来解释其行为。
Existing work on augmenting question answering (QA) models with external knowledge (e.g., knowledge graphs) either struggle to model multi-hop relations efficiently, or lack transparency into the model's prediction rationale. In this paper, we propose a novel knowledge-aware approach that equips pre-trained language models (PTLMs) with a multi-hop relational reasoning module, named multi-hop graph relation network (MHGRN). It performs multi-hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs. The proposed reasoning module unifies path-based reasoning methods and graph neural networks to achieve better interpretability and scalability. We also empirically show its effectiveness and scalability on CommonsenseQA and OpenbookQA datasets, and interpret its behaviors with case studies.
