Substring selection for biomedical document classification
Substring selection for biomedical document classification
复制标题
DOI：
10.1093/bioinformatics/btl350
复制
发表时间：
2006-09-01
期刊：
影响因子：
5.8
通讯作者：
Vucetic, Slobodan
中科院分区：
文献类型：
--
作者：
Han, Bo;Obradovic, Zoran;Vucetic, Slobodan
动机：属性选择是文档分类系统开发的关键步骤。作为标准做法，单词会被词干化，并且信息最丰富的单词会被用作分类中的属性。由于生物医学术语的高度复杂性，通用的词干算法通常是保守的，并且还可能删除信息词干。这可能会导致准确性降低，尤其是当标记文档数量较少时。为了解决这个问题，我们提出了一种省略词干提取的算法，而是使用最具辨别力的子字符串作为属性。结果：该方法在来自 iProLINK 的五组带注释的摘要上进行了测试，这些摘要报告了有关五种蛋白质翻译后修饰的实验证据。实验表明，使用所提出的属性选择时，朴素贝叶斯和支持向量机分类器的性能始终优于使用 Porter 词干分析算法获得的属性（AUC 在 0.86-0.93 范围内）时的性能[ROC 曲线下面积 (AUC) 精度在 0.92-0.97 范围内]。当标记的 clataset 较小时，所提出的方法特别有用。联系方式：vucetic@ist.temple.edu 补充信息：补充数据可从 www.ist.tempie.edu/PIRsupplement 获取。
Motivation: Attribute selection is a critical step in development of document classification systems. As a standard practice, words are stemmed and the most informative ones are used as attributes in classification. Owing to high complexity of biomedical terminology, general-purpose stemming algorithms are often conservative and could also remove informative stems. This can lead to accuracy reduction, especially when the number of labeled documents is small. To address this issue, we propose an algorithm that omits stemming and, instead, uses the most discriminative substrings as attributes.Results: The approach was tested on five annotated sets of abstracts from iProLINKthat report on the experimental evidence about five types of protein post-translational modifications. The experiments showed that Naive Bayes and support vector machine classifiers perform consistently better[with area under the ROC curve (AUC) accuracy in range 0.92-0.97] when usingthe proposed attribute selection than when using attributes obtained by the Porter stemmer algorithm (AUC in 0.86-0.93 range). The proposed approach is particularly useful when labeled clatasets are small.Contact: vucetic@ist.temple.eduSupplementary Information: The supplementary data are available from www.ist.tempie.edu/PIRsupplement.