Combining Syntactic and Semantic Features by SVM for Unrestricted Coreference Resolution

摘要

The paper presents a system for the CoNLL-2011 share task of coreference resolution. The system composes of two components: one for mentions detection and another one for their coreference resolution. For mentions detection, we adopted a number of heuristic rules from syntactic parse tree perspective. For coreference resolution, we apply SVM by exploiting multiple syntactic and semantic features. The experiments on the CoNLL-2011 corpus show that our rule-based mention identification system obtains a recall of 87.69%, and the best result of the SVM-based coreference resolution system is an average F-score 50.92% of the MUC, B-CUBED and CEAFE metrics.