Paper: Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task

ACL ID W11-1902
Title Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2011
Authors

This paper describes the participation of RELAXCOR in the CoNLL-2011 shared task: “Modeling Unrestricted Coreference in Ontonotes“. RELAXCOR is a constraint-based graph partitioning approach to coreference resolution solved by relaxation labeling. The approach combines the strengths of groupwise classifiers and chain formation methods in one global method.