Discriminative Training and Maximum Entropy Models for Statistical Machine Translation

DMCA

Discriminative Training and Maximum Entropy Models for Statistical Machine Translation (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Franz Josef Och , Hermann Ney

Citations:

494 - 29 self

BibTeX

@INPROCEEDINGS{Och02discriminativetraining,
    author = {Franz Josef Och and Hermann Ney},
    title = {Discriminative Training and Maximum Entropy Models for Statistical Machine Translation},
    booktitle = {},
    year = {2002},
    pages = {295--302}
}

OpenURL

Abstract

We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source -channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible hidden variables.

Keyphrases

statistical machine translation discriminative training maximum entropy model direct maximum entropy model target language sentence knowledge source source language sentence possible hidden variable source channel approach feature function special case natural language

DMCA