Multi-engine machine translation with an open-source decoder for statistical machine translation

Authors:
Yu Chen;Andreas Eisele;Christian Federmann;Eva Hasler;Michael Jellinghaus;Silke Theison
Affiliations:
Saarland University, Saarbrücken, Germany;Saarland University, Saarbrücken, Germany and DFKI GmbH, Saarbrücken, Germany;DFKI GmbH, Saarbrücken, Germany;University of Cologne, Germany;Saarland University, Saarbrücken, Germany;Saarland University, Saarbrücken, Germany
Venue:
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Year:
2007

Citing 7
Cited 5

A systematic comparison of various statistical alignment models

Computational Linguistics
Hybrid Language Processing in the Spoken Language Translator

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
Three heads are better than one

ANLC '94 Proceedings of the fourth conference on Applied natural language processing
Learning to select a good translation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Using language and translation models to select the best among outputs from multiple MT systems

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Multi-engine machine translation with voted language model

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
First steps towards multi-engine machine translation

ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts

(Meta-) evaluation of machine translation

StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Using Moses to integrate multiple rule-based machine translation engines into a hybrid system

StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
Combining multi-engine translations with Moses

StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
The UZH system combination system for WMT 2011

WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
A machine-learning framework for hybrid machine translation

KI'12 Proceedings of the 35th Annual German conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe an architecture that allows to combine statistical machine translation (SMT) with rule-based machine translation (RBMT) in a multi-engine setup. We use a variant of standard SMT technology to align translations from one or more RBMT systems with the source text. We incorporate phrases extracted from these alignments into the phrase table of the SMT system and use the open-source decoder Moses to find good combinations of phrases from SMT training data with the phrases derived from RBMT. First experiments based on this hybrid architecture achieve promising results.