Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as well as a few standard benchmarks to assess models Multi-hop QA capabilities. In this paper, we focus on the well-established HotpotQA benchmark dataset, which requires models to perform answer span extraction as well as support sentence prediction. We present two extensions to the SOTA Graph Neural Network (GNN) based model for HotpotQA, Hierarchical Graph Network (HGN): (i) we complete the original hierarchical structure by introducing new edges between the query and context sentence nodes; (ii) in the graph propagation step, we propose a novel extension to Hierarchical Graph Attention Network GATH (Graph ATtention with Hierarchies) that makes use of the graph hierarchy to update the node representations in a sequential fashion. Experiments on HotpotQA demonstrate the efficiency of the proposed modifications and support our assumptions about the effects of model related variables.
翻译:多跳QA(问题解答)是多个文件对一个问题找到答案的任务。近年来,为处理这一复杂任务,提出了若干深学习方法,以及一些评估多跳QA模型能力的标准基准。在本文中,我们侧重于已经确立的HotpotQA基准数据集,该数据集要求模型进行回答跨度提取和支持判决预测。我们为HotpotQA、高层次图网基于SOTA的图形神经网络(GNN)模型提供了两个扩展件:(一) 我们通过在查询和上下文句节点之间引入新的边缘来完成最初的等级结构;(二) 在图表传播步骤中,我们建议对高压图形关注网络(GATH)进行新的扩展,利用图表等级来按顺序更新节点表示。HotpotQA实验显示了拟议修改的效率,并支持我们对模型相关变量效果的假设。