远程监督关系抽取中基于力导向图的关系关系学习
Learning Relation Ties with a Force-Directed Graph in Distant Supervised Relation Extraction
摘要：
关系纽带定义为不同关系之间的相关性和互斥性，是远距离监督关系抽取的关键。现有方法通过贪婪地学习局部依赖关系来对该属性进行建模。然而，他们本质上是有限的，未能捕捉到全球的关系纽带的拓扑结构。因此，它们很容易落入局部最优解。为了解决这个问题，本文提出了一种新的基于力有向图的关系抽取模型来全面学习关系纽带。具体来说，我们首先根据关系的全局同现构建一个图。然后，我们借用物理学中库仑定律的思想，在这个图中引入吸引力和排斥力的概念，来学习关系之间的相关性和互斥性。最后，所获得的关系表示作为一个相互依赖的关系分类器。在大规模基准数据集上的实验结果表明，我们的模型能够建模全球关系纽带，并显着优于其他基线。此外，所提出的力有向图可以作为一个模块，以增强现有的关系抽取系统，并提高其性能。
英文摘要：
Relation ties, defined as the correlation and mutual exclusion between different relations, are critical for distant supervised relation extraction. Existing approaches model this property by greedily learning local dependencies. However, they are essentially limited by failing to capture the global topology structure of relation ties. As a result, they may easily fall into a locally optimal solution. To solve this problem, in this paper, we propose a novel force-directed graph based relation extraction model to comprehensively learn relation ties. Specifically, we first build a graph according to the global co-occurrence of relations. Then, we borrow the idea of Coulomb's Law from physics and introduce the concept of attractive force and repulsive force to this graph to learn correlation and mutual exclusion between relations. Finally, the obtained relation representations are applied as an inter-dependent relation classifier. Experimental results on a large scale benchmark dataset demonstrate that our model is capable of modeling global relation ties and significantly outperforms other baselines. Furthermore, the proposed force-directed graph can be used as a module to augment existing relation extraction systems and improve their performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
