Joint Extraction of Entities and RelationsBased on a Novel Tagging Scheme

The pipelined method treats this task as two separated tasks, i.e., named entity recognition (NER) and relation classification (RC)

然後重點是change the extraction problem to a tagging problem

We use the 「BIES」(Begin, Inside, End,Single) signs to represent the position information of a word in the entity.

tag示例：

模型總體來說是一個LSTM做encoder一個LSTM做decoder

也加了一些LSTM的改造：