Sciweavers

1233 search results - page 102 / 247
» N-gram-based Machine Translation
Sort
View
117
Voted
EMNLP
2007
15 years 5 months ago
Improving Translation Quality by Discarding Most of the Phrasetable
It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the para...
Howard Johnson, Joel D. Martin, George F. Foster, ...
ICASSP
2010
IEEE
15 years 4 months ago
Rapid integration of Parts of Speech information to improve reordering model for English-Farsi Speech to Speech Translation
Integrating Parts of Speech (POS) information to Machine Translation (MT) model usually amounts to significant changes in the MT decoder. We present a method to rapidly integrate...
Sameer Maskey, Bowen Zhou
NAACL
2010
15 years 1 months ago
Accurate Non-Hierarchical Phrase-Based Translation
A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend...
Michel Galley, Christopher D. Manning
CIKM
2010
Springer
15 years 2 months ago
Clickthrough-based translation models for web search: from word models to phrase models
Web search is challenging partly due to the fact that search queries and Web documents use different language styles and vocabularies. This paper provides a quantitative analysis ...
Jianfeng Gao, Xiaodong He, Jian-Yun Nie
ACL
2010
15 years 2 months ago
Training Phrase Translation Models with Leaving-One-Out
Several attempts have been made to learn phrase translation probabilities for phrasebased statistical machine translation that go beyond pure counting of phrases in word-aligned t...
Joern Wuebker, Arne Mauser, Hermann Ney