Dependency Parser for Bengali: the JU System at ICON 2009

This paper reports about our work in the ICON 2009 NLP TOOLS CONTEST: Parsing. We submitted two runs for Bengali. A statistical CRF based model followed by a rule-based post-processing technique has been used. The system has been trained on the NLP TOOLS CONTEST: ICON 2009 datasets. The system demonstrated an unlabeled attachment score (UAS) of 74.09%, labeled attachment score (LAS) of 53.90% and labeled accuracy score (LS) of 61.71% respectively.