arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.09908cs.HCcs.CL
收藏

跨语言德语生物医学信息抽取:从Zero-shot到人在回路

Cross-lingual German Biomedical Information Extraction: from Zero-shot to Human-in-the-Loop

Saarland University(萨尔大学);German Research Center for Artificial Intelligence(德国人工智能研究中心);University of Oldenburg(奥尔登堡大学)

Siting Liang, Mareike Hartmann, Daniel Sonntag

摘要:

本文介绍了我们的项目建议,从德国临床叙述中提取生物医学信息的注释数量有限。我们首先描述了迁移学习和主动学习的应用策略来解决我们的问题。在此之后,我们讨论了设计的用户界面提供模型检查和获得用户注释的交互环境。

英文摘要:

This paper presents our project proposal for extracting biomedical information from German clinical narratives with limited amounts of annotations. We first describe the applied strategies in transfer learning and active learning for solving our problem. After that, we discuss the design of the user interface for both supplying model inspection and obtaining user annotations in the interactive environment.

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。

↑