融合关系标签和位置信息的中文医疗文本因果关系抽取方法研究

Study on the Method of Causality Extraction from Chinese Medical Texts by Integrating Relational Label and Location Information

目的/意义利用因果关系词相对位置辅助深度学习模型,提高因果关系预测能力,挖掘医疗文本增益信息。方法/过程将医疗文本因果关系词相对位置信息表示为关系特征层嵌入预训练语言模型,融合基线模型进行实体识别及关系抽取。结果/结论嵌入关系特征层的模型F1值较基线模型BERT-BiLSTM-CRF和CasRel分别提升2.92个百分点和6.41个百分点,因果关系预测能力较好。

Purpose/Significance The relative positions of causality words are utilized to assist deep learning models to improve causality prediction and mine medical text gain information.Method/Process The relative position information of causality words in medical texts is represented as a relational feature layer embedded in a pre-trained language model,and the baseline model is integrated for entity recognition and relationship extraction.Result/Conclusion The F 1 value of the model embedded in the relational feature layer is improved by 2.92 percentage points and 6.41 percentage points compared with the baseline models BERT-BiLSTM-CRF and CasRel,respectively,with better causal prediction capacity.