To cache or not to cache?: experiments with adaptive models in statistical machine translation

Authors:
Jörg Tiedemann
Affiliations:
Uppsala University, Uppsala/Sweden
Venue:
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Year:
2010

Citing 7
Cited 3

A Cache-Based Natural Language Model for Speech Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
A systematic comparison of various statistical alignment models

Computational Linguistics
Language Model Adaptation Using Mixtures and an Exponentially Decaying Cache

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
Language Modeling for Machine Translation

Language Modeling for Machine Translation
Context adaptation in statistical machine translation using models with exponentially decaying cache

DANLP 2010 Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing

Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation

WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Document-wide decoding for phrase-based statistical machine translation

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
The trouble with SMT consistency

WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We report results of our submissions to the WMT 2010 shared translation task in which we applied a system that includes adaptive language and translation models. Adaptation is implemented using exponentially decaying caches storing previous translations as the history for new predictions. Evidence from the cache is then mixed with the global background model. The main problem in this setup is error propagation and our submissions essentially failed to improve over the competitive baseline. There are slight improvements in lexical choice but the global performance decreases in terms of BLEU scores.