Chemical-induced disease relation extraction via attention-based distant supervision
Chemical-induced disease relation extraction via attention-based distant supervision
复制标题
通过基于注意力的远程监督提取化学诱发的疾病关系
DOI：
10.1186/s12859-019-2884-4
复制
发表时间：
2019-07-22
影响因子：
3
通讯作者：
Zhou, Guodong
中科院分区：
文献类型：
--
作者：
Gu, Jinghang;Sun, Fuqing;Zhou, Guodong
背景自动理解化学-疾病关系（CDR）在生物医学研究和卫生保健的各个领域至关重要。监督机器学习提供了一个可行的解决方案，自动提取生物医学实体之间的关系，从科学文献中，它的成功，但是，在很大程度上取决于大规模的生物医学语料库手动注释与密集的劳动和巨大的investment.ResultsWe提出了一个基于注意力的远程监督模式的BioCreative-V CDR提取任务。句内和句间水平的训练示例都是从比较毒理学数据库（CTD）自动生成的，无需任何人为干预。分别采用基于注意力的神经网络和堆叠式自动编码器网络来归纳学习模型，并提取两级的关系。在合并两个级别的结果之后，可以最终提取文档级CDR。它实现了精度/召回率/F1得分为60.3%/73.8%/66.4%，优于国家的最先进的监督学习系统，而不使用任何注释corpus.ConclusionOur实验表明，远程监督是有前途的生物医学文献中提取化学疾病的关系，并同时捕获本地和全球的注意力功能是有效的注意力为基础的远程监督学习。
BackgroundAutomatically understanding chemical-disease relations (CDRs) is crucial in various areas of biomedical research and health care. Supervised machine learning provides a feasible solution to automatically extract relations between biomedical entities from scientific literature, its success, however, heavily depends on large-scale biomedical corpora manually annotated with intensive labor and tremendous investment.ResultsWe present an attention-based distant supervision paradigm for the BioCreative-V CDR extraction task. Training examples at both intra- and inter-sentence levels are generated automatically from the Comparative Toxicogenomics Database (CTD) without any human intervention. An attention-based neural network and a stacked auto-encoder network are applied respectively to induce learning models and extract relations at both levels. After merging the results of both levels, the document-level CDRs can be finally extracted. It achieves the precision/recall/F1-score of 60.3%/73.8%/66.4%, outperforming the state-of-the-art supervised learning systems without using any annotated corpus.ConclusionOur experiments demonstrate that distant supervision is promising for extracting chemical disease relations from biomedical literature, and capturing both local and global attention features simultaneously is effective in attention-based distantly supervised learning.