Naive Bayes and Decision Trees for Function Tagging.
Mihai Lintean, Vasile Rus · 2007
This paper describes the use of two machine learning tech-niques, naive Bayes and decision trees, to address the task of assigning function tags to nodes in a syntactic parse tree. Function tags are extra functional information, such as log-ical subject or predicate, that can be added to certain nodes in syntactic parse trees. We model the function tags assign-ment problem as a classification problem. Each function tag is regarded as a class and the task is to find what class/tag a given node in a parse tree belongs to from a set of predefined classes/tags. The paper offers the first systematic comparison of the two techniques, naive Bayes and decision trees, for the task of function tags assignment. The comparison is based on a standardized data set.