Edinburgh's Machine Translation Systems for European Language Pairs

Nadir Durrani; Barry Haddow; Kenneth Heafield; Philipp Koehn

Edinburgh's Machine Translation Systems for European Language Pairs

Nadir Durrani, Barry Haddow, Kenneth Heafield, Philipp Koehn

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We validated various novel and recently proposed methods for statistical machine translation on 10 language pairs, using large data resources. We saw gains from optimizing parameters, training with sparse features, the operation sequence model, and domain adaptation techniques. We also report on utilizing a huge language model trained on 126 billion tokens.

Original language	English
Title of host publication	Proceedings of the Eighth Workshop on Statistical Machine Translation
Place of Publication	Sofia, Bulgaria
Publisher	Association for Computational Linguistics
Pages	114-121
Number of pages	8
Publication status	Published - 1 Aug 2013

Access to Document

http://www.aclweb.org/anthology/W13-2212

Cite this

@inproceedings{697ae0b4e1404d849b4dc91aa9118499,

title = "Edinburgh's Machine Translation Systems for European Language Pairs",

abstract = "We validated various novel and recently proposed methods for statistical machine translation on 10 language pairs, using large data resources. We saw gains from optimizing parameters, training with sparse features, the operation sequence model, and domain adaptation techniques. We also report on utilizing a huge language model trained on 126 billion tokens.",

author = "Nadir Durrani and Barry Haddow and Kenneth Heafield and Philipp Koehn",

year = "2013",

month = aug,

day = "1",

language = "English",

pages = "114--121",

booktitle = "Proceedings of the Eighth Workshop on Statistical Machine Translation",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Edinburgh's Machine Translation Systems for European Language Pairs

AU - Durrani, Nadir

AU - Haddow, Barry

AU - Heafield, Kenneth

AU - Koehn, Philipp

PY - 2013/8/1

Y1 - 2013/8/1

N2 - We validated various novel and recently proposed methods for statistical machine translation on 10 language pairs, using large data resources. We saw gains from optimizing parameters, training with sparse features, the operation sequence model, and domain adaptation techniques. We also report on utilizing a huge language model trained on 126 billion tokens.

AB - We validated various novel and recently proposed methods for statistical machine translation on 10 language pairs, using large data resources. We saw gains from optimizing parameters, training with sparse features, the operation sequence model, and domain adaptation techniques. We also report on utilizing a huge language model trained on 126 billion tokens.

M3 - Conference contribution

SP - 114

EP - 121

BT - Proceedings of the Eighth Workshop on Statistical Machine Translation

PB - Association for Computational Linguistics

CY - Sofia, Bulgaria

ER -