Please use this identifier to cite or link to this item:
Title: Confidence based learning of a two-model committee for sequence labeling
Authors: Mančev, Dejan 
Todorovic B.
Issue Date: 1-Dec-2012
Journal: 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings
Abstract: The paper presents the use of a two structural model committee, where the output of the first model together with its confidence is set as the input of the second model. The confidence for the given context of predictions in the sequence is extracted from the alternative hypotheses generated from the first model. We present experiments on the shallow parsing, comparing the performance of the proposed method to the separate models. © 2012 IEEE.
ISBN: 9781467315722
DOI: 10.1109/NEUREL.2012.6419998
Appears in Collections:Naučne i umetničke publikacije

Show full item record


checked on Sep 4, 2020

Google ScholarTM



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