论文标题
READEV：自适应推理提问回答知识图
ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
论文作者
论文摘要
知识图应答（KGQA）涉及使用自然语言查询从知识图（KG）中检索实体。面临的挑战是学会推理与问题相关的kg事实，这些事实是遍历KG实体并导致问题答案。为了促进推理，该问题被解码为指令，这是用于指导KG遍历的密集问题。但是，如果派生的指示与基本的kg信息完全不匹配，则它们可能在无关紧要的情况下导致推理。我们的方法称为READEV，为指导解码和执行提供了一种新方法来推理KGQA推理。为了改善指导解码，我们以自适应方式执行推理，在该推理中，KG感知信息用于迭代更新初始说明。为了提高指令执行，我们使用图神经网络（GNN）效仿了广度优先搜索（BFS）。 BFS策略将指令视为一组，并允许我们的方法即时决定其执行顺序。三个kgqa基准的实验结果表明，与以前的最先进的情况相比，后者的有效性，尤其是当kg不完整或解决复杂问题时。我们的代码可在https://github.com/cmavro/rearev_kgqa上公开获取。
Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Graph (KG) using natural language queries. The challenge is to learn to reason over question-relevant KG facts that traverse KG entities and lead to the question answers. To facilitate reasoning, the question is decoded into instructions, which are dense question representations used to guide the KG traversals. However, if the derived instructions do not exactly match the underlying KG information, they may lead to reasoning under irrelevant context. Our method, termed ReaRev, introduces a new way to KGQA reasoning with respect to both instruction decoding and execution. To improve instruction decoding, we perform reasoning in an adaptive manner, where KG-aware information is used to iteratively update the initial instructions. To improve instruction execution, we emulate breadth-first search (BFS) with graph neural networks (GNNs). The BFS strategy treats the instructions as a set and allows our method to decide on their execution order on the fly. Experimental results on three KGQA benchmarks demonstrate the ReaRev's effectiveness compared with previous state-of-the-art, especially when the KG is incomplete or when we tackle complex questions. Our code is publicly available at https://github.com/cmavro/ReaRev_KGQA.
