Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

EMNLP
2006

favoriteEmaildiscussreport

117views Natural Language Processing» more EMNLP 2006»

Phrasetable Smoothing for Statistical Machine Translation

13 years 5 months ago

Phrasetable Smoothing for Statistical Machine Translation

Download www.iro.umontreal.ca

We discuss different strategies for smoothing the phrasetable in Statistical MT, and give results over a range of translation settings. We show that any type of smoothing is a better idea than the relativefrequency estimates that are often used. The best smoothing techniques yield consistent gains of approximately 1% (absolute) according to the BLEU metric.

George F. Foster, Roland Kuhn, Howard Johnson

Real-time Traffic

Better Idea | EMNLP 2006 | EMNLP 2007 | Smoothing | Statistical MT |

claim paper

Related Content

» Improving Translation Quality by Discarding Most of the Phrasetable

» A Comparison of Pivot Methods for PhraseBased Statistical Machine Translation

» Given Bilingual Terminology in Statistical Machine Translation MWESensitve Word Alignment ...

» Machine Translation by Triangulation Making Effective Use of MultiParallel Corpora

» Hierarchical PitmanYor Language Model for Machine Translation

» Large Language Models in Machine Translation

» Smooth Bilingual NGram Translation

» Phrase Translation Probabilities with ITG Priors and Smoothing as Learning Objective

» Syntactic ReAlignment Models for Machine Translation

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2006
Where	EMNLP
Authors	George F. Foster, Roland Kuhn, Howard Johnson

Comments (0)