Joint Knowledge Graph Completion and Question Answering
Joint Knowledge Graph Completion and Question Answering
复制标题
DOI：
10.1145/3534678.3539289
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Lihui Liu;Boxin Du;Jiejun Xu;Yinglong Xia;H. Tong
中科院分区：
文献类型：
--
作者：
Lihui Liu;Boxin Du;Jiejun Xu;Yinglong Xia;H. Tong
知识图推理在许多现实世界的应用中起着关键作用，例如网络对齐，计算事实检查，推荐等等。在这些应用中，知识图补全（KGC）和基于知识图的多跳问答（Multi-hop KGQA）是两个典型的推理任务。在现有的绝大多数工作中，这两个任务是分开考虑的不同的模型或算法。然而，我们设想KGC和多跳KGQA是密切相关的。因此，这两项任务如果得到适当处理，将相互受益。在这项工作中，我们提出了一个名为BiNet的神经模型来联合处理KGC和多跳KGQA，并将其表述为多任务学习问题。具体来说，我们提出的模型利用了共享的嵌入空间和答案评分模块，这使得这两个任务能够自动共享潜在特征，并学习自然语言问题解码器和答案评分模块之间的交互。与现有的方法相比，所提出的BiNet模型同时解决了多跳KGQA和KGC任务，具有上级性能。实验结果表明，BiNet在广泛的KGQA和KGC基准数据集上的性能优于最先进的方法。
Knowledge graph reasoning plays a pivotal role in many real-world applications, such as network alignment, computational fact-checking, recommendation, and many more. Among these applications, knowledge graph completion (KGC) and multi-hop question answering over knowledge graph (Multi-hop KGQA) are two representative reasoning tasks. In the vast majority of the existing works, the two tasks are considered separately with different models or algorithms. However, we envision that KGC and Multi-hop KGQA are closely related to each other. Therefore, the two tasks will benefit from each other if they are approached adequately. In this work, we propose a neural model named BiNet to jointly handle KGC and multi-hop KGQA, and formulate it as a multi-task learning problem. Specifically, our proposed model leverages a shared embedding space and an answer scoring module, which allows the two tasks to automatically share latent features and learn the interactions between natural language question decoder and answer scoring module. Compared to the existing methods, the proposed BiNet model addresses both multi-hop KGQA and KGC tasks simultaneously with superior performance. Experiment results show that BiNet outperforms state-of-the-art methods on a wide range of KGQA and KGC benchmark datasets.