Title:	Machine Learning for Coreference Resolution: Recent Successes and Future Challenges
Authors:	Ng, Vincent
Keywords:	computer science technical report
Issue Date:	23-Dec-2003
Publisher:	Cornell University
Citation:	http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cis/TR2003-1918
Abstract:	State-of-the-art coreference resolution systems are mostly knowledge-based systems that operate by relying on a set of hand-crafted coreference resolution heuristics. Recently, however, machine learning approaches have been shown to be a promising way to build coreference resolution systems that are more robust than their knowledge-based counterparts. Nevertheless, there are several key issues in existing machine learning approaches to the problem that are either not explored or being overlooked, potentially leading to a deterioration of system performance. This document examines each of these issues in detail and suggests potential solutions.
URI:	http://hdl.handle.net/1813/5630
Appears in Collections:	Computing and Information Science Technical Reports

Files in This Item: File Size Format TR2003-1918.ps 599.85 kB Postscript View/Open

Items in eCommons are protected by copyright, with all rights reserved, unless otherwise indicated.