Extracting entities and relations is an essential task of information extraction. Triplets extracted from a sentence might overlap with each other. Previous methods either did not address the overlapping issues or solved overlapping issues partially. To tackle triplet overlapping problems completely, firstly we extract candidate subjects with a standard span mechanism. Then we present a labeled span mechanism to extract the objects and relations simultaneously, we use the labeled span mechanism to generate labeled spans whose start and end positions indicate the objects, and whose labels correspond to relations of subject and objects. Besides, we design an entity attention mechanism to enhance the information fusion between subject and sentence during extracting objects and relations. We test our method on two public datasets, our method achieves the best performances on these two datasets.

翻译：实体与关系抽取是信息抽取的核心任务。句子中提取的三元组可能相互重叠。现有方法或未解决重叠问题，或仅部分解决。为彻底解决三元组重叠问题，我们首先采用标准跨度机制提取候选主语，继而提出标记跨度机制以同步抽取宾语与关系——通过该机制生成标记跨度，其起止位置指示宾语，标签对应主宾语间的关联关系。此外，我们设计了实体注意力机制，在抽取宾语与关系过程中增强主语与句子间的信息融合。在两个公开数据集上的实验表明，本方法取得了最优性能。