Abstract: According to Tsinghua Chinese Treebank annotation methods, the authors extracted relation words and marked their categories. Then syntax, lexical and position features of automatic syntax tree with and without functional marker were extracted to recognize and classify relation words. Experiment results show that relative recognition accuracy is 95.7%, and relation words classification F1 is 77.2%.

Key words: relation words in compound sentences, Tsinghua Chinese Treebank, relation words recognition, relation words classification

摘要： 根据清华汉语树库的标注方法, 利用规则从中提取复句关系词并标注其类别, 然后分别抽取带功能标记和不带功能标记的自动句法树的句法、词法、位置特征, 进行复句关系词的识别和分类。实验结果表明, 复句关系词判断准确率达95.7%, 复句关系词类别判断F1值为77.2%。

关键词: 复句关系词, 清华汉语树库, 关系词识别, 关系词分类