Enforcing Consistency on Coreference Sets
نویسنده
چکیده
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 straightforward binding constraints give rise to (local) exclusiveness of markables, transitivity propagates these restrictions and enforces the re-computation of coreference sets.
منابع مشابه
Coreference Resolution with Loose Transitivity Constraints
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 d...
متن کاملARRAU: Linguistically-Motivated Annotation of Anaphoric Descriptions
This paper presents a second release of the ARRAU dataset: a multi-domain corpus with thorough linguistically motivated annotation of anaphora and related phenomena. Building upon the first release almost a decade ago, a considerable effort had been invested in improving the data both quantitatively and qualitatively. Thus, we have doubled the corpus size, expanded the selection of covered phen...
متن کاملCoreference Annotation Scheme and Relation Types for Hindi
This paper describes a coreference annotation scheme, coreference annotation specific issues and their solutions through our proposed annotation scheme for Hindi. We introduce different co-reference relation types between continuous mentions of the same coreference chain such as ‘Part-of’, ‘Function-value pair’ etc. We used Jaccard similarity based Krippendorff‘s’ alpha to demonstrate consisten...
متن کاملCoreference Resolution with Reconcile
Despite the existence of several noun phrase coreference resolution data sets as well as several formal evaluations on the task, it remains frustratingly difficult to compare results across different coreference resolution systems. This is due to the high cost of implementing a complete end-to-end coreference resolution system, which often forces researchers to substitute available gold-standar...
متن کاملJoint Learning for Coreference Resolution with Markov Logic
Pairwise coreference resolution models must merge pairwise coreference decisions to generate final outputs. Traditional merging methods adopt different strategies such as the bestfirst method and enforcing the transitivity constraint, but most of these methods are used independently of the pairwise learning methods as an isolated inference procedure at the end. We propose a joint learning model...
متن کامل