arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00775cs.IRcs.CL
收藏

基于临床笔记的自监督答案检索

Self-supervised Answer Retrieval on Clinical Notes

Beuth University of Applied Sciences(博伊特应用科学大学)

Paul Grundmann, Sebastian Arnold, Alexander Löser

摘要:

从长文档中检索答案段落是一项复杂的任务,需要对话语和文档上下文进行语义理解。我们特别在临床场景中处理这一挑战,医生根据诊断和其他潜在的医疗方面检索患者队列。我们引入CAPR,一个基于规则的自我监督目标,用于训练Transformer语言模型,以进行特定领域的段落匹配。此外,我们贡献了一个新的检索数据集的基础上,临床笔记模拟这种情况下,一个大型语料库的临床笔记。我们将我们的目标应用于四个基于转换器的架构:上下文文档向量,双,多和交叉编码器。根据我们对MIMIC-III和其他三个医疗数据集的广泛评估,我们报告说CAPR在检索特定领域的段落方面优于强基线,并有效地概括了基于规则和人类标记的段落。这使得模型功能强大,特别是在zero-shot场景中,只有有限的训练数据可用。

英文摘要:

Retrieving answer passages from long documents is a complex task requiring semantic understanding of both discourse and document context. We approach this challenge specifically in a clinical scenario, where doctors retrieve cohorts of patients based on diagnoses and other latent medical aspects. We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching. In addition, we contribute a novel retrieval dataset based on clinical notes to simulate this scenario on a large corpus of clinical notes. We apply our objective in four Transformer-based architectures: Contextual Document Vectors, Bi-, Poly- and Cross-encoders. From our extensive evaluation on MIMIC-III and three other healthcare datasets, we report that CAPR outperforms strong baselines in the retrieval of domain-specific passages and effectively generalizes across rule-based and human-labeled passages. This makes the model powerful especially in zero-shot scenarios where only limited training data is available.

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。

↑