论文标题
MT-Clinical Bert：通过多任务学习缩放临床信息提取
MT-Clinical BERT: Scaling Clinical Information Extraction with Multitask Learning
论文作者
论文摘要
临床笔记包含有关患者的大量重要但不可读的信息。自动提取此信息的系统依赖于大量培训数据，其创建资源有限。此外，它们是局面发展的。这意味着在特定于任务的系统之间无法共享任何信息。这种瓶颈不必要地使实际应用复杂化，降低了每个解决方案的性能能力，并将管理多个信息提取系统的工程债务联系起来。我们通过开发多任务临床BERT来应对这些挑战：一个单一的深度学习模型，同时执行八个临床任务，涵盖实体提取，phi识别，语言识别和相似性，通过在任务之间共享表示形式。我们发现，我们的单个系统在所有特定于特定于任务的系统中都可以竞争性能，同时也从推理时受益于大量计算福利。
Clinical notes contain an abundance of important but not-readily accessible information about patients. Systems to automatically extract this information rely on large amounts of training data for which their exists limited resources to create. Furthermore, they are developed dis-jointly; meaning that no information can be shared amongst task-specific systems. This bottle-neck unnecessarily complicates practical application, reduces the performance capabilities of each individual solution and associates the engineering debt of managing multiple information extraction systems. We address these challenges by developing Multitask-Clinical BERT: a single deep learning model that simultaneously performs eight clinical tasks spanning entity extraction, PHI identification, language entailment and similarity by sharing representations amongst tasks. We find our single system performs competitively with all state-the-art task-specific systems while also benefiting from massive computational benefits at inference.
