|
|||||
|
|
| 基于框架的汉语篇章结构生成和篇章关系识别 | |
| 引用本文： | 吕国英,苏 娜,李 茹,王智强,柴清华.基于框架的汉语篇章结构生成和篇章关系识别[J].中文信息学报,2015,29(6):98-109. |
| 作者姓名： | 吕国英 苏 娜 李 茹 王智强 柴清华 |
| 作者单位： | 1. 山西大学 计算机与信息技术学院,山西 太原 030006; 2. 山西大学 计算智能与中文信息处理教育部重点实验室,山西 太原 030006; 3. 山西大学 外国语学院,山西 太原 030006 |
| 基金项目： | 国家自然科学基金(61373082);山西省科技基础条件平台建设项目(2014091004-0103);山西省回国留学人员科研资助项目(2013-015);国家863计划项目(2015AA015407);中国民航大学信息安全测评中心开放课题基金项目(CACC-ISECCA-201402) |
| 摘 要： | 针对汉语篇章分析的三个任务: 篇章单元切割、篇章结构生成和篇章关系识别,该文提出引入框架语义进行分析研究。首先基于框架构建了汉语篇章连贯性描述体系以及相应语料库;然后抽取句首、依存句法、短语结构、目标词、框架等特征,分别训练基于最大熵的篇章单元间有无关系分类器和篇章关系分类器;最后采用贪婪算法自下向上生成篇章结构树。实验证明,框架语义可以有效切割篇章单元,并且框架特征可以有效提升篇章结构以及篇章关系的识别效果。 |
| 关 键 词： | 篇章单元 篇章结构 篇章关系 贪婪算法 |
Frame-Based Discourse Structure Modeling andRelation Recognition for Chinese Sentence |
|
| LV Guoying,SU Na,LI Ru,WANG Zhiqiang,CHAI Qinghua.Frame-Based Discourse Structure Modeling andRelation Recognition for Chinese Sentence[J].Journal of Chinese Information Processing,2015,29(6):98-109. | |
| Authors: | LV Guoying SU Na LI Ru WANG Zhiqiang CHAI Qinghua |
| Affiliation: | 1. School of Computer & Information Technology, Shanxi University, Taiyuan, Shanxi 030006, China; 2. Key laboratory of Computation Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan, Shanxi 030006, China; 3. School of Foreign Languages, Shanxi University, Taiyuan, Shanxi 030006, China) |
| Abstract: | Frame semantics is introduced to the research of Chinese discourse analysis which includes three subtasks discourse segmentation, discourse structure modeling and discourse relation recognition. First, the Chinese discourse coherence framework and a corresponding corpus is built based on frame semantics. Then two kinds of maximum entropy classifiers are applied to recognize the relation between discourse units and the class of discourse relation based on lexical features, dependency parser features, syntactic parser features, target features and frame sematic features. Finally, we use probability of the relation existence between discourse units to generate the discourse structure by greedy bottom-up method. Experimental results show that frame sematic can segment discourse units effectively and frame sematic feature can improve the performance of discourse structure construction and discourse relation recognition. Key words Discourse units; Discourse Structure; Discourse Relation; Greedy Bottom-up Method |
| Keywords: | Discourse units Discourse Structure Discourse Relation Greedy Bottom-up Method |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |
