Factors influencing dependency parsing of coordinating structure

Coordinating structure is a special phenomena with high frequence in human languages. It enjoys a special status in linguistic theories especially in dependency grammars, which require the exceptional treatment. This paper proposes three schemes to analyse coordinating structure and builds dependency treebanks for automatic parsing. We find that different schemes to annotate and parse the coordinating structure bring some distinctions in precision and other aspects. The factors, such as the part-of-speech categories matching with their syntactic functions, may play an important role in dependency parsing. We also calculate the mean dependency distance of three schemes, and the result shows that single-directional and smaller mean dependency distance is helpful for better machine learning and higher precision.