A multi-aspect comparison study of supervised word sense disambiguation
A multi-aspect comparison study of supervised word sense disambiguation
复制标题
DOI：
10.1197/jamia.m1533
复制
发表时间：
2004-07-01
影响因子：
6.4
通讯作者：
Friedman, C
中科院分区：
文献类型：
--
作者：
Liu, HF;Teller, V;Friedman, C
目的：本研究的目的是探讨监督式词义消歧（WSD； supervised machine learning for elimination of a context中一个术语的词义消歧）中不同方面之间的关系，并比较生物医学领域的监督式词义消歧与普通英语领域的监督式词义消歧。方法：本研究涉及三个数据集（生物医学缩略语数据集、通用生物医学术语数据集和通用英语数据集）。作者实现了三种机器学习算法，包括(1)朴素贝叶斯（NBL）和决策列表（TDLL），(2)它们对决策列表的适应（ODLL）和(3)它们的混合监督学习（MSL）。有六种特征表示（各种搭配组合、词袋、定向词袋等）和五种窗口大小（2、4、6、8和10）。结果：有监督的WSD仅适用于有足够的感官标记的实例，并且每个感官至少有几十个实例。搭配与邻近的词结合在一起是适合上下文的选择。对于与生物医学意义无关的术语，应该使用大的窗口大小，例如整个段落，而对于一般英语单词，应该使用4到10之间的中等窗口大小。本文实现的决策表分类器对缩略语的分类性能优于传统的决策表分类器。然而，另外两组的情况正好相反。此外，作者的混合监督学习是稳定的，并且在所有集合中都优于其他方法。结论：本研究发现，监督式WSD的不同方面是相互依赖的。本文提出的实验方法可用于为每个歧义项选择最佳的有监督WSD分类器。
Objective: The aim of this study was to investigate relations among different aspects in supervised word sense disambiguation (WSD; supervised machine learning for disambiguating the sense of a term in a context) and compare supervised WSD in the biomedical domain with that in the general English domain.Methods: The study involves three data sets (a biomedical abbreviation data set, a general biomedical term data set, and a general English data set). The authors implemented three machine-learning algorithms, including (1) naive Bayes (NBL) and decision lists (TDLL), (2) their adaptation of decision lists (ODLL), and (3) their mixed supervised learning (MSL). There were six feature representations (various combinations of collocations, bag of words, oriented bag of words, etc.) and five window sizes (2, 4, 6, 8, and 10).Results: Supervised WSD is suitable only when there are enough sense-tagged instances with at least a few dozens of instances for each sense. Collocations combined with neighboring words are appropriate selections for the context. For terms with unrelated biomedical senses, a large window size such as the whole paragraph should be used, while for general English words a moderate window size between 4 and 10 should be used. The performance of the authors' implementation of decision list classifiers for abbreviations was better than that of traditional decision list classifiers. However, the opposite held for the other two sets. Also, the authors' mixed supervised learning was stable and generally better than others for all sets.Conclusion: From this study, it was found that different aspects of supervised WSD depend on each other. The experiment method presented in the study can be used to select the best supervised WSD classifier for each ambiguous term.