An Empirical Study on the Effect of Morphological and Lexical Features in Persian Dependency Parsing

This paper investigates the impact of different morphological and lexical information on data-driven dependency parsing of Persian, a morphologically rich language. We explore two state-of-the-art parsers, namely MSTParser andMaltParser, on the recently released Persian dependency treebank and establish some baselines for dependency parsing performance. Three sets of issues are addressed in our experiments: effects of using gold and automatically derived features, finding the best features for the parser, and a suitable way to alleviate the data sparsity problem. The final accuracy is 87.91% and 88.37% labeled attachment scores for MaltParser and MSTParser, respectively.