● Syntactic Parsing: MST Parser, training and

Conclusion & Future Work ● The overall ranking of the system is #7 in the closed challenge, and #2 in the open challenge ● The results clearly show that the integration of HPSG parsing results in the semantic role labeling task brings substantial performance improvement. The conclusion from Zhang et al. (2008) on English has been reconfirmed on multiple languages, even where grammar coverage is low ● The gain is more significant on out-of-domain tests, indicating that the hybrid system is more robust to cross-domain variation ● The closed SRL system needs to be improved in the future Results In this paper we present our syntactic and semantic dependency parsing system, which extends the system of Zhang, Wang, & Uszkoreit (2008) in the multilingual direction, and achieves 76.49 average macro F1 Score on the closed joint task. Substantial improvements to the open SRL task have been observed that are attributed to the HPSG parses with hand-crafted grammars