论文标题
用于多主推理的关系图卷积神经网络：一项比较研究
Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Study
论文作者
论文摘要
Multihop问题回答是一项复杂的自然语言处理任务，需要多个推理步骤才能找到给定问题的正确答案。先前的研究探索了基于图神经网络来解决此任务的模型的使用。已经提出了各种体系结构，包括关系图卷积网络（RGCN）。对于这些许多节点类型及其之间的关系，已经引入了这些节点类型，例如简单的实体共发生，建模核心发音或通过中介实体从问题到答案的“推理路径”。然而，关于哪些关系，节点类型，嵌入和体系结构对此任务最有益的周到分析仍然缺失。在本文中，我们探讨了许多基于RGCN的多ihop QA模型，图形关系和节点嵌入，并经验探索了每个模型对Wikihop数据集中多霍普QA性能的影响。
Multihop Question Answering is a complex Natural Language Processing task that requires multiple steps of reasoning to find the correct answer to a given question. Previous research has explored the use of models based on Graph Neural Networks for tackling this task. Various architectures have been proposed, including Relational Graph Convolutional Networks (RGCN). For these many node types and relations between them have been introduced, such as simple entity co-occurrences, modelling coreferences, or "reasoning paths" from questions to answers via intermediary entities. Nevertheless, a thoughtful analysis on which relations, node types, embeddings and architecture are the most beneficial for this task is still missing. In this paper we explore a number of RGCN-based Multihop QA models, graph relations, and node embeddings, and empirically explore the influence of each on Multihop QA performance on the WikiHop dataset.
