Relation Extraction systems train an extractor by aligning relation instances in Knowledge Base with a large amount of labeled corpora. Since the labeled datasets are very expensive, Distant Supervision Relation Extraction (DSRE) utilizes rough corpus annotated with Knowledge Graph to reduce the cost of acquisition. Nevertheless, the data noise problem limits the performance of the DSRE. Dependency trees can be used to filter the wrong-labeled instances in the distant supervision bag. However, existing dependency tree relation extraction strategies are all based on manually-set paths between the subject and object entities, and suffer from the problem of pruning the trees too aggressively or too insufficiently. To circumvent the shortcomings, in this paper, we propose a novel DSRE framework ${\mathrm{A}}^2$DSRE, based on the Adaptive dependency-path and Additional KG supervision. To obtain the dependency paths related to entity relations adaptively, we introduce an advanced graph neural network—GeniePath into DSRE, which assigns higher weights to those direct neighbor words that contribute more to relation prediction through breadth exploration, and conducts depth exploration to determine the correlation between relations and high-order neighbors. In this way, the irrelevant nodes are pruned while the relevant nodes are kept, our method can obtain more appropriate paths associated with relations. At the same time, to further reduce the noises in the data, we incorporate additional supervision information from the knowledge graph by retracting the margin between the representation of the bag and the pre-training knowledge graph embedding. Extensive numerical experiments validate the effectiveness of our new method.

关系提取系统通过将知识库中的关系实例与大量标记的语料库对齐来训练提取器。由于标记的数据集非常昂贵，因此远距离监督关系提取（DSRE）利用标注有知识图的粗糙语料库来降低获取成本。但是，数据噪声问题限制了DSRE的性能。依赖树可用于过滤远程监管包中标记错误的实例。然而，现有的依赖树关系提取策略全部基于主题和对象实体之间的手动设置的路径，并且存在过分地或过于不足地修剪树的问题。为了克服这些缺点，本文提出了一种新颖的DSRE框架${\mathrm{一种}}^2$DSRE，基于A适应性依赖路径和AKG的传统监督。为了自适应地获得与实体关系有关的依赖路径，我们在DSRE中引入了高级图神经网络GeniePath，该网络将较高的权重分配给那些通过广度探索对关系预测有更大贡献的直接相邻词，并进行深度探索以确定相关性关系和高阶邻居之间的关系。这样，不相关的节点被修剪而相关的节点被保留，我们的方法可以获得与关系相关的更合适的路径。同时，为了进一步减少数据中的噪声，我们通过缩回袋子表示形式和预训练知识图嵌入之间的边距，并从知识图中合并了其他监管信息。