Text-level Discourse Dependency Parsing

• DOI: 10.3115/v1/p14-1003
• Publication Date: 2015-06-17T07:05:16Z
• Authors: Sujian Li; Liang Wang; Ziqiang Cao; Wenjie Li
• Keywords: Dependency grammar; Tree (set theory); Margin (machine learning); Parse tree

Previous researches on Text-level discourse parsing mainly made use of constituency structure to parse the whole document into one tree.In this paper, we present limitations based and first propose dependency directly represent relations between elementary units (EDUs).The state-of-the-art techniques, Eisner algorithm maximum spanning tree (MST) algorithm, are adopted an optimal arcfactored model large-margin learning techniques.Experiments show that our parsers achieve a competitive performance text-level parsing.