篇章话题结构分析针对篇章的意图性，是篇章级语义分析的基础。目前自然语言处理研究的重点聚焦在词法和句法层面，对篇章内在规律的研究相对较少，缺乏对篇章话题进行有效分析的理论方法体系，严重制约了基于篇章级语义分析的相关应用。本项目将从理论体系探索、语料库构建和计算模型研究等方面系统深入开展汉语篇章话题结构分析的研究：1）研究汉语篇章话题结构组织的规律和特点，建立一套适用于汉语篇章话题结构表示与分析的理论体系，拟采用一种基于主述位理论的汉语篇章话题结构表示方式，基于微观话题链构建汉语篇章话题结构表示体系；2）提出一套汉语篇章微观话题结构标注规范，并结合自举学习和主动学习方法半自动构建一定规模的高质量汉语篇章话题结构标注语料库资源；3）研究篇章话题结构的动态生成过程，提出并实现一套基于主位推进理论的汉语篇章话题结构分析动态计算模型。

The analysis of discourse topic structure focuses on the discourse intension and plays a fundamental role to discourse-level semantic analysis. Currently, most of research in NLP focuses on morphological and syntactic levels and there is much less research on the inherent regulations in discourse. This results in the lack of theoretical and computational methodologies towards effective discourse topic analysis and severely restricts its wide applications. This project addresses Chinese discourse topic structure analysis from following aspects:.1) Studying the general regulations and special characteristics in the structure organization of Chinese discourse topic and building a theoretical framework suitable to the representation and analysis of Chinese discourse topic structure. Specially, a micro-topic scheme based on theme-rheme theory is proposed to represent Chinese discourse topic structure and a Chinese discourse topic framework will be constructed on micro-topic chains..2) Proposing an annotation scheme for Chinese discourse topic structure and semi-automatically building a certain-scale Chinese discourse topic corpus of high quality via integrating bootstrapping and active learning methods..3) Studying the dynamic forming process of discourse topic structure. Based on the thematic progression theory, a dynamic computational model to implement Chinese discourse topic analysis is proposed.