Text-level Discourse Dependency Parsing
Text-level Discourse Dependency Parsing
复制标题
DOI：
10.3115/v1/p14-1003
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Sujian Li;Liang Wang;Ziqiang Cao;Wenjie Li
中科院分区：
文献类型：
--
作者：
Sujian Li;Liang Wang;Ziqiang Cao;Wenjie Li
以往的文本级语篇分析研究主要是利用群体结构将整个文档解析成一个语篇树。在本文中，我们指出了基于群体的语篇分析的局限性，并首次提出使用依赖结构直接表示基本语篇单元之间的关系。采用最先进的依赖解析技术，即Eisner算法和最大生成树（MST）算法，基于分解模型和大边际学习技术，解析出最优语篇依赖树。实验表明，我们的语篇依赖解析器在文本级语篇解析上取得了较好的效果。
Previous researches on Text-level discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent the relations between elementary discourse units (EDUs). The state-of-the-art dependency parsing techniques, the Eisner algorithm and maximum spanning tree (MST) algorithm, are adopted to parse an optimal discourse dependency tree based on the arcfactored model and the large-margin learning techniques. Experiments show that our discourse dependency parsers achieve a competitive performance on text-level discourse parsing.