JavaScript is disabled for your browser. Some features of this site may not work without it.
Reconcile: A Coreference Resolution Research Platform

Author
Stoyanov, Veselin; Cardie, Claire; Gilbert, Nathan; Riloff, Ellen; Buttler, David; Hysom, David
Abstract
We have created a software infrastructure called Reconcile that is a platform for the development of learning-based noun phrase (NP) coreference resolution systems. Reconcile’s architecture was designed to facilitate the rapid creation of coreference resolutions systems, easy implementation of new feature sets and approaches to coreference resolution, and empirical evaluation of coreference resolvers across a variety of benchmark data sets and standard scoring metrics. Reconcile is written in Java and can be easily customized with different subcomponents, feature sets, and parameter settings. In this report, we describe Reconcile’s architecture, processing pipeline, and the subcomponents and algorithms that are currently implemented and available in Reconcile. We also present experimental results showing that Reconcile can be used to create a coreference resolver which achieves performance levels comparable to state-of-the-art systems on six benchmark data sets.
Sponsorship
This research was supported in part by Lawrence
Livermore National Laboratory subcontract
B573245 and the Department of Homeland
Security under ONR Grant N0014-07-1-0152.
Date Issued
2010-04-13Subject
natural language processing; coreference resolution
Type
technical report