基于PDTB体系的隐式篇章关系识别  

Recognizing PDTB Style Implicit Discourse Relations

作　　者：李生[1] 孔芳[1] 周国栋[1] LI Sheng KONG Fang ZHOU Guodong(School of Computer Sciences and Technology, Soochow University, Suzhou, Jiangsu 215006, China)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006

出　　处：《中文信息学报》2016年第4期81-89,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61472264;61273320;61333018;61331011);国家863项目(2012AA011102)

摘　　要：识别隐式篇章关系是篇章分析领域中非常有挑战的一个任务。该文基于PDTB语料提出一个隐式篇章分析识别方法,使用传统的特征如动词,极性和句法推导规则等,系统分析了它们对隐式篇章分析的影响。我们利用全部标注数据构建多个分类器并使用加法规则融合分类结果,此外还通过前向特征选择算法确定各分类任务最优的特征集。实验结果表明该方法能显著提升隐式篇章分析的性能。Recognizing implicit discourse relation is a challenging task in discourse parsing.In this paper,we propose an implicit discourse relation recognizing method in the Penn Discourse Treebank（PDTB）considering some traditional features（e.g.,verbs,polarity,production rules,and so on）,and provide a systematic analysis for our implicit discourse relation method.We apply all labeled data to build multiple classifiers,and use the adding rule to identify final classification result for each instance.We also use forward feature selection method to select an optimal feature subset for each classification task.Experimental results in the PDTB corpus show that our proposed method can significantly improve the state-of-the-art performance of recognizing implicit discourse relation.

关 键 词：篇章处理 隐式篇章关系 宾州篇章树库 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]