Comparison of extended lexicon models in search and rescoring for SMT

Authors:
Saša Hasan;Hermann Ney
Affiliations:
RWTH Aachen University, Germany;RWTH Aachen University, Germany
Venue:
NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Year:
2009

Citing 4
Cited 5

The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Refined lexicon models for statistical machine translation using a maximum entropy approach

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Word-sense disambiguation for machine translation

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Triplet lexicon models for statistical machine translation

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing

Extending statistical machine translation with discriminative and trigger-based lexicon models

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Better filtration and augmentation for hierarchical phrase-based translation rules

ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Jane: open source hierarchical translation, extended with reordering and lexicon models

WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
A comparison of segmentation methods and extended lexicon models for Arabic statistical machine translation

Machine Translation
Jane: an advanced freely available hierarchical machine translation toolkit

Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show how the integration of an extended lexicon model into the decoder can improve translation performance. The model is based on lexical triggers that capture long-distance dependencies on the sentence level. The results are compared to variants of the model that are applied in reranking of n-best lists. We present how a combined application of these models in search and rescoring gives promising results. Experiments are reported on the GALE Chinese-English task with improvements of up to +0.9% BLEU and -1.5% TER absolute on a competitive baseline.