Clausal parsing helps data-driven dependency parsing: Experiments with Hindi

This paper investigates clausal data-driven dependency parsing. We first motivate a clause as the minimal parsing unit by correlating interand intra-clausal relations with relation type, depth, arc length and non-projectivity. This insight leads to a two-stage formulation of parsing where intra-clausal relations are identified in the 1 stage and inter-clausal relations are identified in the 2 stage. We compare two ways of implementing this idea, one based on hard constraints (similar to the one used in constraint-based parsing) and one based on soft constraints (using a kind of parser stacking). Our results show that the approach using hard constraints seems most promising and performs significantly better than single-stage parsing. Our best result gives significant increase in LAS and UAS, respectively, over the previous best result using single-stage parsing.