At the time, the field of statistical machine translation was all but dead.

The idea behind statistical machine translation comes from information theory.

It is widely used to train statistical machine translation systems.

Problems that statistical machine translation have to deal with include:

Dr. Knight acknowledges that statistical machine translation is far from perfect.

Google has claimed that promising results were obtained using a proprietary statistical machine translation engine.

The most frequently cited benefits of statistical machine translation over rule-based approach are:

NiuTrans is a statistical machine translation system.

Statistical Machine Translation - includes introduction to research, conference, corpus and software listings.

Some of the production system design and statistical machine translation system for Google Translate.

Little further research in machine translation was conducted until the late 1980s, when the first statistical machine translation systems were developed.

His research activities are in statistical machine translation, natural language processing and machine learning where he has co-authored more than 50 scientific papers.

Initially it was designed for research purposes in statistical machine translation (SMT).

Koehn authored a book titled Statistical Machine Translation in 2009.

Decoding algorithm in statistical machine translation.

Currently a large amount of research is being done into statistical machine translation and example-based machine translation.

Annotated list of statistical natural language processing resources - Includes links to freely available statistical machine translation software.

Despite the progress being made in statistical machine translation, some researchers remain skeptical, preferring to focus their efforts on language-specific translation techniques.

The decoder (which is part of a complete statistical machine translation toolkit) is the de facto benchmark for research in the field.

Statistical machine translation do not work well between languages that have significantly different word orders (e.g. Japanese and European languages).

The Moses decoder is a platform for developing Statistical machine translation systems given a parallel corpus for any language pair.

Phrases like these, called "N-grams" (with N representing the number of terms in a given phrase) are the basic building blocks of statistical machine translation.

Other approaches to machine translation, including statistical machine translation, also use bilingual corpora to learn the process of translation.

(2007) "Moses: Open Source Toolkit for Statistical Machine Translation".

Statistical machine translation - in which computers essentially learn new languages on their own instead of being "taught" the languages by bilingual human programmers - has taken off.