论文标题
医学文本的几次学习：系统评价
Few-shot learning for medical text: A systematic review
论文作者
论文摘要
目的：很少的学习方法（FSL）方法需要少量的标记培训实例。由于许多医学主题在实际设置中具有注释的文本数据有限，因此基于FSL的自然语言处理（NLP）方法具有实质性的希望。我们旨在进行系统审查，以探索医疗NLP的FSL方法的状态。材料和方法：我们使用PubMed/Medline，Embase，ACL选集和IEEE Xplore数字图书馆搜索了2016年1月至2021年8月之间发表的文章。为了识别最新的相关方法，我们还通过Google Scholar搜索了其他来源，例如预印式服务器（例如MedRxiv）。我们包括了所有涉及FSL和任何类型的医学文本的文章。我们根据数据源，AIM（S），训练集大小，主要方法/方法（ES）和评估方法提取文章。结果：31个研究符合我们的纳入标准 - 2018年之后发表；自2020年以来，22（71％）。概念提取/命名实体识别是最常见的任务（13/31; 42％），其次是文本分类（10/31; 32％）。 21个（68％）的研究重建了现有数据集以合成几乎没有弹头的情况，而模拟于III是最常用的数据集（7/31; 23％）。常见方法包括具有注意机制（12/31; 39％），典型网络（8/31; 26％）和元学习（6/31; 19％）的FSL。讨论：尽管FSL在生物医学NLP中具有潜力，但与独立于域的FSL相比，进展受到限制。这可能是由于标准化，公共数据集的匮乏以及FSL方法对生物医学主题的相对表现不佳。用于生物医学FSL的专业数据集创建和释放可以通过启用比较分析来帮助开发方法。
Objective: Few-shot learning (FSL) methods require small numbers of labeled instances for training. As many medical topics have limited annotated textual data in practical settings, FSL-based natural language processing (NLP) methods hold substantial promise. We aimed to conduct a systematic review to explore the state of FSL methods for medical NLP. Materials and Methods: We searched for articles published between January 2016 and August 2021 using PubMed/Medline, Embase, ACL Anthology, and IEEE Xplore Digital Library. To identify the latest relevant methods, we also searched other sources such as preprint servers (eg., medRxiv) via Google Scholar. We included all articles that involved FSL and any type of medical text. We abstracted articles based on data source(s), aim(s), training set size(s), primary method(s)/approach(es), and evaluation method(s). Results: 31 studies met our inclusion criteria-all published after 2018; 22 (71%) since 2020. Concept extraction/named entity recognition was the most frequently addressed task (13/31; 42%), followed by text classification (10/31; 32%). Twenty-one (68%) studies reconstructed existing datasets to create few-shot scenarios synthetically, and MIMIC-III was the most frequently used dataset (7/31; 23%). Common methods included FSL with attention mechanisms (12/31; 39%), prototypical networks (8/31; 26%), and meta-learning (6/31; 19%). Discussion: Despite the potential for FSL in biomedical NLP, progress has been limited compared to domain-independent FSL. This may be due to the paucity of standardized, public datasets, and the relative underperformance of FSL methods on biomedical topics. Creation and release of specialized datasets for biomedical FSL may aid method development by enabling comparative analyses.
