Study on the Method of Causality Extraction from Chinese Medical Texts by Integrating Relational Label and Location Information
10.3969/j.issn.1673-6036.2024.01.004
- VernacularTitle: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
- Author:
Weining ZHANG
1
;
Xifeng SHEN
;
Meiting LI
;
Dongping GAO
Author Information
1. 中国医学科学院/北京协和医学院医学信息研究所/图书馆 北京 100020
- Keywords:
natural language processing;
causality extraction;
pre-training model;
BERT;
medical text
- From:
Journal of Medical Informatics
2024;45(1):21-26
- CountryChina
- Language:Chinese
-
Abstract:
Purpose/Significance The relative positions of causality words are utilized to assist deep learning models to improve cau-sality 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 enti-ty recognition and relationship extraction.Result/Conclusion The F1 value of the model embedded in the relational feature layer is im-proved by 2.92 percentage points and 6.41 percentage points compared with the baseline models BERT-BiLSTM-CRF and CasRel,re-spectively,with better causal prediction capacity.
