Combining the best of two worlds: A hybrid approach to multilingual coreference resolution

We describe our system for the CoNLL-2012 shared task, which seeks to model corefer-ence in OntoNotes for English, Chinese, and Arabic. We adopt a hybrid approach to coreference resolution, which combines the strengths of rule-based methods and learning-based methods. Our official combined score over all three languages is 56.35. In particu-lar, our score on the Chinese test set is the best among the participating teams.