摘要
词义消歧要解决的问题是如何让计算机理解多义词在特定的上下文环境中具体代表的语义。多义词多为常用词,在语料中出现的频率很高。确立一种合适的建模方法,并选择一种行之有效的机器学习方法,是解决词义消歧问题的首要任务。贝叶斯模型在词义消歧中的构建和实现上相对要简便易用,机器学习过程也简洁高效,特别是贝叶斯模型作为词义消歧工具,无论是实现的效率,还是消歧的效果都比较理想。
Word Sense Disambiguation is developed to solve the problem of how to make the computer understand the meaning of some specific ambiguity in a specific context. Ambiguity is always frequently used. The most important task of word sense disambiguation is to establish an appropriate modeling method and select an effective way of machine learning. Bayesian model is relatively easy-to-use in the construction and realization, and the machine learning process is also simple and efficient. Especially Bayesian model, as a research tool for word sense disambiguation, is an ideal choice for its high efficiency and satisfying results.
出处
《计算机时代》
2009年第7期63-64,共2页
Computer Era
关键词
词义消歧
机器学习
贝叶斯模型
最大熵模型
word sense disambiguation
machine learning
Bayesian model
maximum entropy model
