Paper: Hybrid Multilingual Parsing with HPSG for SRL

ACL ID W09-1204
Title Hybrid Multilingual Parsing with HPSG for SRL
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
  • Yi Zhang (German Research Center for Artificial Intelligence, Saarbrucken Germany)
  • Rui Wang (Saarland University, Saarbrucken Germany)
  • Stephan Oepen (University of Oslo, Oslo Norway)

In this paper we present our syntactic and se- mantic dependency parsing system submitted to both the closed and open challenges of the CoNLL 2009 Shared Task. The system ex- tends the system of Zhang, Wang, & Uszko- reit (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. †