中文语义角色标注的特征工程

基于统计机器学习的语义角色标注在自然语言处理领域越来越受到重视,丰富多样的特征直接决定语义角色标注系统的性能。本文针对中文的特点,在英文语义角色标注特征的基础上,提出了一些更有效的新特征和组合特征: 例如,句法成分后一个词、谓语动词和短语类型的组合、谓语动词类别信息和路径的组合等,并在Chinese Proposition Bank(CPB)语料数据上,使用最大熵分类器进行了实验,系统F-Score由89.76%增加到91.31%。结果表明,这些新特征和组合特征显著提高了系统的性能。因此,目前进行语义角色标注应集中精力寻找丰富有效的特征。

Feature Engineering for Chinese Semantic Role Labeling

In the natural language processing field,researchers have experienced a growth of interest in semantic role labeling by applying statistical and machine-learning methods.Using rich features is the most important part of semantic parsing system.In this paper,some new effective features and combination features are proposed,such as next word of the constituent,predicate and phrase type combination,predicate class and path combination,and so on.And then we report the experiments on the dataset from Chinese Proposition Bank(CPB).After these new features used,the final system improves the F-Score from 89.76% to 91.31%.The results show that the performance of the system has a statistically significant increase.Therefore it is very important to find better features for semantic role labeling.