论文标题
致密原子：朝着密集连接的原子，具有较高的知识覆盖范围和巨大的多跳路路径
Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths
论文作者
论文摘要
Atomic是一个大规模常识知识图（CSKG），其中包含日常知识三胞胎，即{head事件，关系，尾巴事件}。单跳注释方式使原子化成为一组独立的两部分图，该图忽略了不同双方图中事件之间的众多联系，因此导致知识覆盖率和多跳路径的短缺。在这项工作中，我们旨在构建具有高知识覆盖范围和大量多跳路的密集原子。原子中的事件首先将其标准化为一致的模式。然后，我们提出了一种称为rel-cskgc的CSKG完成方法，以预测给定头部事件和三胞胎的尾巴事件的关系，并根据原子中现有的三胞胎训练CSKG完成模型。我们最终利用该模型来完成原子中缺失的链接，并因此构建致密原子。对原子的注释亚图的自动和人类评估都证明了Rel-Cskgc比强质基础的优势。我们进一步对统计，人类评估和简单下游任务的密集原子进行了广泛的评估，所有这些都证明了知识覆盖和多跳路的密集原子的优势。 https://github.com/nustm/dense-atomic均可公开获得Rel-CSKGC和密度原子的源代码。
ATOMIC is a large-scale commonsense knowledge graph (CSKG) containing everyday if-then knowledge triplets, i.e., {head event, relation, tail event}. The one-hop annotation manner made ATOMIC a set of independent bipartite graphs, which ignored the numerous links between events in different bipartite graphs and consequently caused shortages in knowledge coverage and multi-hop paths. In this work, we aim to construct Dense-ATOMIC with high knowledge coverage and massive multi-hop paths. The events in ATOMIC are normalized to a consistent pattern at first. We then propose a CSKG completion method called Rel-CSKGC to predict the relation given the head event and the tail event of a triplet, and train a CSKG completion model based on existing triplets in ATOMIC. We finally utilize the model to complete the missing links in ATOMIC and accordingly construct Dense-ATOMIC. Both automatic and human evaluation on an annotated subgraph of ATOMIC demonstrate the advantage of Rel-CSKGC over strong baselines. We further conduct extensive evaluations on Dense-ATOMIC in terms of statistics, human evaluation, and simple downstream tasks, all proving Dense-ATOMIC's advantages in Knowledge Coverage and Multi-hop Paths. Both the source code of Rel-CSKGC and Dense-ATOMIC are publicly available on https://github.com/NUSTM/Dense-ATOMIC.
