@文章{info:doi/10.2196/41136，作者=“李永斌和辉，林虎和邹丽萍和李湖阳和徐，罗王晓华和蔡晓华，Stephanie”，标题=“基于句法依赖特征的多头注意模型的生物医学文本关系提取:建模研究”，期刊=“JMIR Med Inform”，年=“2022”，月=“十月”，日=“20”，卷=“10”，数=“10”，页=“e41136”，关键词=“生物医学关系提取;深度学习;功能组合;多头的关注;加关注;句法依赖特征;句法依赖图;背景:随着生物医学文献的快速扩展，生物医学信息提取越来越受到研究者的关注。其中，两个实体之间的关系提取是一个长期的研究课题。目的:本研究旨在完成2019生物医学自然语言处理研讨会开放共享任务的2个多类关系提取任务:细菌-生物群落(BB-rel)关系提取任务和植物种子发育(SeeDev-binary)二元关系提取任务。 In essence, these 2 tasks are aimed at extracting the relation between annotated entity pairs from biomedical texts, which is a challenging problem. Methods: Traditional research methods adopted feature- or kernel-based methods and achieved good performance. For these tasks, we propose a deep learning model based on a combination of several distributed features, such as domain-specific word embedding, part-of-speech embedding, entity-type embedding, distance embedding, and position embedding. The multi-head attention mechanism is used to extract the global semantic features of an entire sentence. Meanwhile, we introduced a dependency-type feature and the shortest dependency path connecting 2 candidate entities in the syntactic dependency graph to enrich the feature representation. Results: Experiments show that our proposed model has excellent performance in biomedical relation extraction, achieving F1 scores of 65.56{\%} and 38.04{\%} on the test sets of the BB-rel and SeeDev-binary tasks. Especially in the SeeDev-binary task, the F1 score of our model is superior to that of other existing models and achieves state-of-the-art performance. Conclusions: We demonstrated that the multi-head attention mechanism can learn relevant syntactic and semantic features in different representation subspaces and different positions to extract comprehensive feature representation. Moreover, syntactic dependency features can improve the performance of the model by learning dependency relation between the entities in biomedical texts. ", issn="2291-9694", doi="10.2196/41136", url="https://medinform.www.mybigtv.com/2022/10/e41136", url="https://doi.org/10.2196/41136", url="http://www.ncbi.nlm.nih.gov/pubmed/36264604" }