1.Tagging
    2017ZhengJoint Extraction of Entities and Relations Based on a Novel Tagging Scheme
    p：将关系抽取任务转化为序列标注任务
    n：每个实体只能属于一个关系三元组
    2020WeiA Novel Cascade Binary Tagging Framework for Relational Triple Extraction
    p：双重标记网络：先标记主体，再对任意关系标记客体

    思考：
    对于Tagging，对于重复实体数据集，是否存在对实体的过学习

    2.Table-filling
    2019FuGraphRel Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
    p：采用图卷积方法分析节点和边

    思考：**
    对于Table-filling，引入了图表结构，能否用图像语义分割方法

    3.Seq2Seq
    2018ZengExtracting Relational Facts by an End-to-End Neural Model with Copy Mechanism
    p：利用Copy MeChanism处理triple-overlapping problem
    n：However, they used a copy mechanism to copy only the last token of the entities, thus this model could not extract the full entity names.
    Also, their best performing model used a separate decoder to extract each tuple which limited the power of their model.
    2019ZengLearning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning