NE-LP：基于归一化熵和损失预测的中文分词主动学习算法
NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs
摘要：
医院信息系统中的电子健康档案（Electronic Health Records，EHR）包含了患者的诊断和治疗信息，因此EHR对临床数据采掘至关重要。中文分词（CWS）是挖掘过程中的一个基本而重要的任务，现有的分词方法大多依赖于大规模的人工标注数据。由于注释是耗时且昂贵的，因此已经致力于诸如主动学习的技术来定位用于建模的信息量最大的样本。本文顺应这一趋势，提出了一种针对EHR中CWS的主动学习方法。具体地说，提出了一种结合归一化熵和损失预测（NE-LP）的采样策略来选择最具代表性的数据。同时，为了最小化学习的计算成本，我们提出了一个联合模型，包括一个词分割器和一个损失预测模型。此外，为了捕捉相邻字符之间的交互，在联合模型中还应用了二元组特征。为了说明NE-LP的有效性，我们对上海中医药大学附属曙光医院的EHR进行了实验。结果表明，NE-LP始终优于传统的基于不确定性的采样策略的主动学习在CWS。
英文摘要：
Electronic Health Records (EHRs) in hospital information systems contain patients' diagnosis and treatments, so EHRs are essential to clinical data mining. Of all the tasks in the mining process, Chinese Word Segmentation (CWS) is a fundamental and important one, and most state-of-the-art methods greatly rely on large-scale of manually-annotated data. Since annotation is time-consuming and expensive, efforts have been devoted to techniques, such as active learning, to locate the most informative samples for modeling. In this paper, we follow the trend and present an active learning method for CWS in EHRs. Specically, a new sampling strategy combining Normalized Entropy with Loss Prediction (NE-LP) is proposed to select the most representative data. Meanwhile, to minimize the computational cost of learning, we propose a joint model including a word segmenter and a loss prediction model. Furthermore, to capture interactions between adjacent characters, bigram features are also applied in the joint model. To illustrate the effectiveness of NE-LP, we conducted experiments on EHRs collected from the Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine. The results demonstrate that NE-LP consistently outperforms conventional uncertainty-based sampling strategies for active learning in CWS.
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。
