Large and Diverse Language Models for Statistical Machine Translation

Holger Schwenk; Philipp Koehn

Large and Diverse Language Models for Statistical Machine Translation

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

Abstract

This paper presents methods to combine large language models trained from diverse text sources and applies them to a state-of-art French–English and Arabic–English machine translation system. We show gains of over 2 BLEU points over a strong baseline by using continuous space language models in re-ranking.

Original language	English
Title of host publication	Third International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India, January 7-12, 2008
Pages	661-666
Number of pages	6
Publication status	Published - 2008

Access to Document

Schwenk Koehn 2008 Large and Diverse Language Models for Statistical Machine TranslationFinal published version, 383 KB

http://aclweb.org/anthology/I/I08/I08-2089.pdf

Cite this

@inproceedings{a48f6f55eab54008acb01de3da3c4d24,

title = "Large and Diverse Language Models for Statistical Machine Translation",

abstract = "This paper presents methods to combine large language models trained from diverse text sources and applies them to a state-of-art French–English and Arabic–English machine translation system. We show gains of over 2 BLEU points over a strong baseline by using continuous space language models in re-ranking.",

author = "Holger Schwenk and Philipp Koehn",

year = "2008",

language = "English",

pages = "661--666",

booktitle = "Third International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India, January 7-12, 2008",

}

TY - GEN

T1 - Large and Diverse Language Models for Statistical Machine Translation

AU - Schwenk, Holger

AU - Koehn, Philipp

PY - 2008

Y1 - 2008

N2 - This paper presents methods to combine large language models trained from diverse text sources and applies them to a state-of-art French–English and Arabic–English machine translation system. We show gains of over 2 BLEU points over a strong baseline by using continuous space language models in re-ranking.

AB - This paper presents methods to combine large language models trained from diverse text sources and applies them to a state-of-art French–English and Arabic–English machine translation system. We show gains of over 2 BLEU points over a strong baseline by using continuous space language models in re-ranking.

M3 - Conference contribution

SP - 661

EP - 666

BT - Third International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India, January 7-12, 2008

ER -