Czech-English phrase-based machine translation

Authors:
Ondřej Bojar;Evgeny Matusov;Hermann Ney
Affiliations:
Institute of Formal and Applied Linguistics, ÚFAL MFF UK, Praha, Czech Republic;Lehrstuhl für Informatik 6, Computer Science Department, RWTH Aachen University, Aachen, Germany;Lehrstuhl für Informatik 6, Computer Science Department, RWTH Aachen University, Aachen, Germany
Venue:
FinTAL'06 Proceedings of the 5th international conference on Advances in Natural Language Processing
Year:
2006

Citing 7
Cited 1

A systematic comparison of various statistical alignment models

Computational Linguistics
Czech-English dependency-based machine translation

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Greedy decoding for statistical machine translation in almost linear time

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
A hierarchical phrase-based model for statistical machine translation

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Symmetric word alignments for statistical machine translation

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Modeling syntax of free word-order languages: dependency analysis by reduction

TSD'05 Proceedings of the 8th international conference on Text, Speech and Dialogue

English-to-Czech factored machine translation

StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe experiments with Czech-to-English phrase-based machine translation. Several techniques for improving translation quality (in terms of well-established measure BLEU) are evaluated. In total, we are able to achieve BLEU of 0.36 to 0.41 on the examined corpus of Wall Street Journal texts, outperforming all other systems evaluated on this language pair.