arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.09335cs.CLcs.AI
收藏

基于分层知识图谱的生物医学事件提取

Biomedical Event Extraction with Hierarchical Knowledge Graphs

Information Sciences Institute, University of Southern California(南加州大学信息科学研究所);University of California, Los Angeles(加州大学洛杉矶分校)

Kung-Hsiang Huang, Mu Yang, Nanyun Peng

摘要:

生物医学事件提取是理解科学语料库中描述的生物分子相互作用的关键。其中一个主要的挑战是识别与非指示性触发词相关联的嵌套结构化事件。我们建议将领域知识从统一医学语言系统(UMLS)的预训练语言模型通过图边条件注意力网络(GEANet)和层次图表示。为了更好地识别触发词,每个句子首先接地的句子图的基础上,联合建模的层次知识图谱从UMLS。接地图,然后传播GEANet,一种新的图神经网络,用于增强能力,推断复杂的事件。在BioNLP 2011 GENIA事件提取任务中,我们的方法在所有事件和复杂事件上分别实现了1.41%和3.19%的F1改进。消融研究证实了GEANet和分级KG的重要性。

英文摘要:

Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicative trigger words. We propose to incorporate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model via Graph Edge-conditioned Attention Networks (GEANet) and hierarchical graph representation. To better recognize the trigger words, each sentence is first grounded to a sentence graph based on a jointly modeled hierarchical knowledge graph from UMLS. The grounded graphs are then propagated by GEANet, a novel graph neural networks for enhanced capabilities in inferring complex events. On BioNLP 2011 GENIA Event Extraction task, our approach achieved 1.41% F1 and 3.19% F1 improvements on all events and complex events, respectively. Ablation studies confirm the importance of GEANet and hierarchical KG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑