Coreference Resolution with Loose Transitivity Constraints
نویسندگان
چکیده
Our system treats coreference resolution as an integer linear programming (ILP) problem. Extending Denis and Baldridge (2007) and Finkel andManning (2008)’s work, we exploit loose transitivity constraints on coreference pairs. Instead of enforcing transitivity closure constraints, which brings O(n3) 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.
منابع مشابه
Enforcing Consistency on Coreference Sets
We show that intra-sentential binding constraints can act as global constraints that via transitivity enforce consistency on coreference sets. This yields about 5 % increase in performance. In our model, the probabilities of a baseline classi er for coreference resolution are used as weights in an optimization model. The underlying integer linear programming (ILP) speci cation is straightforwar...
متن کاملEnforcing Transitivity in Coreference Resolution
A desirable quality of a coreference resolution system is the ability to handle transitivity constraints, such that even if it places high likelihood on a particular mention being coreferent with each of two other mentions, it will also consider the likelihood of those two mentions being coreferent when making a final assignment. This is exactly the kind of constraint that integer linear progra...
متن کاملCorpus based coreference resolution for Farsi text
"Coreference resolution" or "finding all expressions that refer to the same entity" in a text, is one of the important requirements in natural language processing. Two words are coreference when both refer to a single entity in the text or the real world. So the main task of coreference resolution systems is to identify terms that refer to a unique entity. A coreference resolution tool could be...
متن کاملGlobal joint models for coreference resolution and named entity classification
In this paper, we combine models for coreference, anaphoricity and named entity classification as a joint, global inference problem using Integer Linear Programming (ilp). Our constraints ensure: (i) coherence between the final decisions of the three local models, and (ii) transitivity of multiple coreference decisions. This approach provides significant f -score improvements on the ace dataset...
متن کاملAn Incremental Model for Coreference Resolution with Restrictive Antecedent Accessibility
We introduce an incremental model for coreference resolution that competed in the CoNLL 2011 shared task (open regular). We decided to participate with our baseline model, since it worked well with two other datasets. The benefits of an incremental over a mention-pair architecture are: a drastic reduction of the number of candidate pairs, a means to overcome the problem of underspecified items ...
متن کامل