Abstract:
This paper proposes a novel method for sentence-level Chinese discourse tree building. The authors
constrcut a Chinese discourse annotated corpus in the framework of Rhetorical Structure Theory, and propose a
ranking-like SVM (SVM-R) model to automatically build the tree structure, which can capture the relative
associated strength among three consecutive text spans rather than only two adjacent spans. The experimental
results show that proposed SVM-R method significantly outperforms state-of-the-art methods in discourse parsing
accuracy. It is also demonstrated that the useful features for discourse tree building are consistent with Chinese
language characteristics.

Key words: discourse tree building, ranking method, Chinese discourse annotated corpus

摘要：

提出一种自动分析汉语小句级句际关系树的新方法。在修辞结构理论体系下, 构建一个汉语句际关系标注语料库。不同于传统的只关心相邻两个单元的方法, 提出一种类排序模型(SVM-R), 自动构建汉语句际关系的树结构, 旨在把握相邻3 个单元之间的关联强度。实验结果表明, 所提出的SVM-R模型对句际关系树的分析显著优于传统方法。最后提出并验证了丰富的、适合于汉语句际关系分析的语言特征。

关键词: 句际关系树构建, 排序方法, 汉语句际关系语料库