Extracting relational triples from texts is a fundamental task in knowledge graph construction. The popular way of existing methods is to jointly extract entities and relations using a single model, which often suffers from the overlapping triple problem. That is, there are multiple relational triples that share the same entities within one sentence. In this work, we propose an effective cascade dual-decoder approach to extract overlapping relational triples, which includes a text-specific relation decoder and a relation-corresponded entity decoder. Our approach is straightforward: the text-specific relation decoder detects relations from a sentence according to its text semantics and treats them as extra features to guide the entity extraction; for each extracted relation, which is with trainable embedding, the relation-corresponded entity decoder detects the corresponding head and tail entities using a span-based tagging scheme. In this way, the overlapping triple problem is tackled naturally. Experiments on two public datasets demonstrate that our proposed approach outperforms state-of-the-art methods and achieves better F1 scores under the strict evaluation metric. Our implementation is available at https://github.com/prastunlp/DualDec.

翻译：从文本中提取关系三重是知识图构建中的一项基本任务。现有方法的流行方式是使用单一的模型联合提取实体和关系,这往往受到重叠的三重问题的影响。也就是说,在一个句子内存在多个关联三重问题,在同一个句子内共有相同实体。在这项工作中,我们建议采用有效的级联双解码法来提取重叠关系三重问题,其中包括一个文本特定关系解码器和对应关系的实体解码器。我们的方法很简单:文本特定关系解码器根据其文字语义学从一个句子中探测关系,并将它们作为指导实体提取的附加特征对待;对于每一个提取关系,即与可训练的嵌入,关系corpond-corped实体解码器使用一个基于跨区域标记的图案来检测相应的头和尾实体。这样,重叠的三重问题就自然解决了。对两个公共数据集的实验表明,我们拟议的方法超越了“艺术状态”的方法,并在严格评估下实现更好的F1Dzub/Decast。我们可以在 http://Decgast上进行实施。