Hybrid Dependency Parser with Segmented Treebanks and Reparsing

摘要：

　　We propose a hybrid dependency parsing pipeline which combines transition-based parser and graph-based parser,and use segmented treebanks to train transition-based parsers as subparsers in front end,and then propose a constrained Eisners algorithm to reparse their outputs.We build the pipeline to investigate the influence on parsing accuracy when training with different segmentations of training data and find a convenient method to obtain parsing reliability score while achieving state-of-the-art parsing accuracy.Our results show that the pipeline with segmented training dataset could improve accuracy through reparsing while providing parsing reliability score.

关键词： Hybrid dependency parsing Constrained Eisners algorithm Parsing reliability score Transition-based parser Graph-based parser

作者: Fuxiang Wu Fugen Zhou

作者单位: Image Processing Center,Beihang University,Beihang,China

会议类型: 国际会议

会议名称: The 2015 Chinese Intelligent Automation Conference(2015中国智能自动化会议)

会议地点: 福州

会议语种:英文

页码: 53-60

在线出版日期: 2015-05-08（万方平台首次上网日期，不代表论文的发表时间）