Abstract
Clinical information extraction (e.g., 2010 i2b2/VA challenge) usually presents tasks of concept recognition, assertion classification, and relation extraction. Jointly modeling the multi-stage tasks in the clinical domain is an underexplored topic. The existing independent task setting (reference inputs given in each stage) makes the joint models not directly comparable to the existing pipeline work. To address these issues, we define a joint task setting and propose a novel end-to-end system to jointly optimize three-stage tasks. We empirically investigate the joint evaluation of our proposal and the pipeline baseline with various embedding techniques: word, contextual, and in-domain contextual embeddings. The proposed joint system substantially outperforms the pipeline baseline by +0.3, +1.4, +3.1 for the concept, assertion, and relation F1. This work bridges joint approaches and clinical information extraction. The proposed approach could serve as a strong joint baseline for future research. The code is publicly available.
Abstract (translated)
临床信息提取（例如，2010年i2b2/VA挑战赛）通常包括概念识别、断言分类和关系抽取等任务。在临床领域中联合建模多阶段任务是一个较少被探索的课题。现有的独立任务设置（每个阶段都有给定的参考输入），使得联合模型无法直接与现有流水线工作进行比较。为了解决这些问题，我们定义了一个联合任务设置，并提出了一种新颖的端到端系统以共同优化三个阶段的任务。我们通过使用各种嵌入技术：词嵌入、上下文嵌入和领域内上下文嵌入来进行实验性评估，比较了我们的提案与流水线基线的联合评价结果。提出的联合系统在概念、断言和关系F1分数上分别比流水线基线高出0.3、1.4和3.1分。这项工作将联合方法与临床信息提取联系起来，所提出的方法可以作为未来研究的强大联合基准。代码已公开发布。
URL
https://arxiv.org/abs/2603.07487
