DICE: Data-Efficient Clinical Event Extraction with Generative Models
DICE: Data-Efficient Clinical Event Extraction with Generative Models
复制标题
DOI：
10.48550/arxiv.2208.07989
复制
发表时间：
2022-08
影响因子：
3
通讯作者：
Mingyu Derek Ma;Alex S. Taylor;Wei Wang;Nanyun Peng
中科院分区：
文献类型：
--
作者：
Mingyu Derek Ma;Alex S. Taylor;Wei Wang;Nanyun Peng
临床领域的事件提取是一个未开发的研究领域。训练数据的缺乏沿着大量具有模糊实体边界的特定领域术语，使得任务特别具有挑战性。在本文中，我们介绍了DICE，一个强大的和数据高效的临床事件提取生成模型。DICE将事件提取作为一个条件生成问题，并引入了一个对比学习目标，以准确地确定生物医学提及的边界。DICE还与事件提取任务联合训练辅助提及识别任务，以更好地识别实体提及边界，并进一步引入特殊标记以将识别的实体提及作为其各自任务的触发和参数候选。为了对临床事件提取进行基准测试，我们基于现有的临床信息提取数据集MACROBAT组成了第一个具有参数注释的临床事件提取数据集MACROBAT-EE。我们的实验证明了DICE在临床和新闻领域事件提取中的最新性能，特别是在低数据设置下。
Event extraction for the clinical domain is an under-explored research area. The lack of training data along with the high volume of domain-specific terminologies with vague entity boundaries makes the task especially challenging. In this paper, we introduce DICE, a robust and data-efficient generative model for clinical event extraction. DICE frames event extraction as a conditional generation problem and introduces a contrastive learning objective to accurately decide the boundaries of biomedical mentions. DICE also trains an auxiliary mention identification task jointly with event extraction tasks to better identify entity mention boundaries, and further introduces special markers to incorporate identified entity mentions as trigger and argument candidates for their respective tasks. To benchmark clinical event extraction, we compose MACCROBAT-EE, the first clinical event extraction dataset with argument annotation, based on an existing clinical information extraction dataset MACCROBAT. Our experiments demonstrate state-of-the-art performances of DICE for clinical and news domain event extraction, especially under low data settings.