ResNet结合BiGRU的关系抽取混合模型

A Hybrid Model for Relation Extraction via ResNet & BiGRU

关系抽取主要目的是将非结构化或半结构化描述的自然语言文本转化成结构化数据,其主要负责从文本中识别出实体,抽取实体间的语义关系。就关系抽取任务而言,当前流行的网络结构是仅使用CNN作为编码器,经过多层卷积操作后,对池化的结果进行softmax分类。还有部分工作则使用RNN并结合Attention机制对最后的结果做分类。这些网络结构在远程监督带噪声的关系抽取任务中表现并不理想。该文主要根据ResNet残差块的特性,提出了一种混合模型,它有效融合,ResNet和BiGRU,将带有残差特性的CNN和双向RNN结合起来,最后融入注意力机制来完成基于远程监督的关系抽取任务。实验验证了该混合模型在远程监督的噪声过滤方面的有效性。在NYT-Freebase数据集上,P@N值相比使用单一ResNet提高了2.9%。另外,该文所建混合模型可以很轻易地移植应用到其他NLP任务中。

The main purpose of relational extraction is to transform unstructured or semi-structured text into structured data,focusing on identifying entities from text and especially extracting semantic relationships between entities.This paper explores a hybrid model of ResNet and BiGRU.Based on the characteristics of the ResNet,we combine residual learning CNN with RNN on the extraction of entity relation tasks.The residual block,RNN and attention mechanism are simultaneously used for the weakly-supervised relation extraction.Experimental results indicate that,on NYT-Freebase dataset,the P@N results are improved by 2.9% compared with the single ResNet.