Training method of remote supervision relation extraction model and related device

The invention provides a training method of a remote supervision relation extraction model and a related device, wherein the remote supervision relation extraction model comprises a word embedding layer, a feature extraction layer and an output layer, the feature extraction layer comprises a circulation layer and a convolution layer, and the output layer comprises a bag-level maximum pool layer and a softmax layer. Contextual information of entities in sentences is obtained through a loop layer, and fine-grained features are extracted from position sentences through a convolution layer. Manualfeatures and NLP tools are omitted, and remote supervision of relation extraction is enhanced. The method comprises the following steps of: for an entity relationship, packaging a plurality of positive samples into a sentence bag, packaging a plurality of negative samples into a sentence bag, and training a model, so that the influence caused by wrong labels is reduced. 本发明提供了一种遥监督关系抽取模型的训练方法及相关装置，遥监督关系抽取模型包括词嵌入层、特征提取层和输