We describe methods for translating a text given in multiple source languages into a single target language. The goal is to improve translation quality in applications where the ultimate goal is to translate the same document into many languages. We describe a statistical approach and two specific statistical models to deal with this problem. Our method is generally applicable as it is independent of specific models, languages or application domains. We evaluate the approach on a multilingual corpus covering all eleven official European Union languages that was collected automatically from the Internet. In various tests we show that these methods can significantly improve translation quality. As a side effect, we also compare the quality of statistical machine translation systems for many European languages in the same domain.
[1]
Hermann Ney,et al.
Improved Alignment Models for Statistical Machine Translation
,
1999,
EMNLP.
[2]
Kenneth Ward Church,et al.
A Program for Aligning Sentences in Bilingual Corpora
,
1993,
CL.
[3]
Hermann Ney,et al.
Improved Statistical Alignment Models
,
2000,
ACL.
[4]
Hermann Ney,et al.
A Comparison of Alignment Models for Statistical Machine Translation
,
2000,
COLING.
[5]
Robert L. Mercer,et al.
The Mathematics of Statistical Machine Translation: Parameter Estimation
,
1993,
CL.
[6]
Hermann Ney,et al.
Improving SMT quality with morpho-syntactic analysis
,
2000,
COLING.
[7]
Hermann Ney,et al.
HMM-Based Word Alignment in Statistical Translation
,
1996,
COLING.