Advanced End-to-End Relation Extraction with Deep Neural Networks

摘要 连接各种生物医学实体的关系构成了使生物医学数据科学成为可能的重要资源 应用程序和知识发现。关系信息横跨翻译科学的光谱 从生物学(例如，蛋白质-蛋白质相互作用)到翻译生物信息学(例如，基因-疾病关联)， 并最终应用于临床护理(例如，药物与药物的相互作用)。科学家报告在NAT中新发现的关系- 通过同行评议的文献使用乌拉尔语言，医生可以在临床笔记中进行交流。更多 最近，患者也在社交媒体上报告了副作用和不良事件。随着指数级增长 文本数据，生物医学自然语言处理(BioNLP)方法的进步正在为 从文本中提取生物医学关系。BRE目前的大多数工作都遵循流水线方法，包括 命名实体识别(NER)、实体规范化(EN)和关系分类识别(RC)作为子任务。他们 通常会遭遇错误滚雪球--管道组件中的错误会导致更多的下游错误 -导致整个BRE系统的性能较低。这种情况导致了对不同 BRE子桩是单独进行的。在这项提议中，我们提出了严格的端到端评估的有力理由 其中关系将从原始文本中产生。我们提出了新的深度神经网络结构 以端到端的方式建模BRE，并直接在单个 经过。我们还将我们的体系结构扩展到n元和跨句设置，其中两个以上的实体可以 即使关系是在多个句子中表达的，也需要链接。我们还建议创建两个 新的金标准BRE数据集，一个用于药物-疾病治疗关系，另一个是fi首个同类数据集 用于联合药物治疗。我们的主要假设是，我们的端到端提取模型将产生超过 与传统管道相比，性能更佳。我们通过(1)检验这一点。基于内在评估的 关于使用几个黄金标准数据集的标准绩效衡量标准和(2)。面向外部应用程序 使用用例在信息检索、问题回答和知识中提取关系的评估 基地完工。作为该项目的一部分开发的所有软件和数据都将向公众开放，并 我们希望这将促进BRE系统的严格端到端基准。

ABSTRACT Relations linking various biomedical entities constitute a crucial resource that enables biomedical data science applications and knowledge discovery. Relational information spans the translational science spectrum going from biology (e.g., protein–protein interactions) to translational bioinformatics (e.g., gene–disease associations), and eventually to clinical care (e.g., drug–drug interactions). Scientists report newly discovered relations in nat- ural language through peer-reviewed literature and physicians may communicate them in clinical notes. More recently, patients are also reporting side-effects and adverse events on social media. With exponential growth in textual data, advances in biomedical natural language processing (BioNLP) methods are gaining prominence for biomedical relation extraction (BRE) from text. Most current efforts in BRE follow a pipeline approach containing named entity recognition (NER), entity normalization (EN), and relation classification (RC) as subtasks. They typically suffer from error snowballing — errors in a component of the pipeline leading to more downstream errors — resulting in lower performance of the overall BRE system. This situation has lead to evaluation of different BRE substaks conducted in isolation. In this proposal we make a strong case for strictly end-to-end evaluations where relations are to be produced from raw text. We propose novel deep neural network architectures that model BRE in an end-to-end fashion and directly identify relations and corresponding entity spans in a single pass. We also extend our architectures to n-ary and cross-sentence settings where more than two entities may need to be linked even as the relation is expressed across multiple sentences. We also propose to create two new gold standard BRE datasets, one for drug–disease treatment relations and another first of a kind dataset for combination drug therapies. Our main hypothesis is that our end-to-end extraction models will yield supe- rior performance when compared with traditional pipelines. We test this through (1). intrinsic evaluations based on standard performance measures with several gold standard datasets and (2). extrinsic application oriented assessments of relations extracted with use-cases in information retrieval, question answering, and knowledge base completion. All software and data developed as part of this project will be made available for public use and we hope this will foster rigorous end-to-end benchmarking of BRE systems.