Abstract

We present two systems for bridging resolution, which we submitted to the CRAC shared task on bridging anaphora resolution in the ARRAU corpus (track 2): a rule-based approach following Hou et al. 2014 and a learning-based approach. The re-implementation of Hou et al. 2014 achieves very poor performance when being applied to ARRAU. We found that the reasons for this lie in the different bridging annotations: whereas the rule-based system suggests many referential bridging pairs, ARRAU contains mostly lexical bridging. We describe the differences between these two types of bridging and adapt the rule-based approach to be able to handle lexical bridging. The modified rule-based approach achieves reasonable performance on all (sub)-tasks and outperforms a simple learning-based approach.