iROVER: improving system combination with classification

Authors:
D. Hillard;B. Hoffmeister;M. Ostendorf;R. Schlüter;H. Ney
Affiliations:
University of Washington, Seattle, WA;RWTH Aachen University, Aachen, Germany;University of Washington, Seattle, WA;RWTH Aachen University, Aachen, Germany;RWTH Aachen University, Aachen, Germany
Venue:
NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers
Year:
2007

Citing 1
Cited 2

BoosTexter: A Boosting-based Systemfor Text Categorization

Machine Learning - Special issue on information retrieval

Complexity of finding the BLEU-optimal hypothesis in a confusion network

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
The RWTH system combination system for WMT 2011

WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an improved system combination technique, iROVER, Our approach obtains significant improvements over ROVER, and is consistently better across varying numbers of component systems. A classifier is trained on features from the system lattices, and selects the final word hypothesis by learning cues to choose the system that is most likely to be correct at each word location. This approach achieves the best result published to date on the TC-STAR 2006 English speech recognition evaluation set.