Coreference Resolution with Loose Transitivity Constraints
Xinxin Li, Xuan hang Wang, Shuhan Qi · 2011
Our system treats coreference resolution as an integer linear programming (ILP) problem. Extending Denis and Baldridge (2007) and Finkel and Manning (2008)’s work, we exploit loose transitivity constraints on coreference pairs. Instead of enforcing transitivity closure constraints, which brings complexity, we employ a strategy to reduce the number of constraints without large performance decrease, i.e., eliminating coreference pairs with probability below a threshold�. Experimental results show that it achieves a better performance than pairwise classifiers. 1