Using monolingual source-language data to improve MT performance

@inproceedings{Ueffing2006UsingMS,
  title={Using monolingual source-language data to improve MT performance},
  author={Nicola Ueffing},
  booktitle={IWSLT},
  year={2006}
}
Statistical machine translation systems are usually trained on large amounts of bilingual text and of monolingual text in the target language. In this paper, we will present a self-training approach which additionally explores the use of monolingual source text, namely the documents to be translated, to improve the system performance. An initial version of the translation system is used to translate the source text. Among the generated translations, target sentences of low quality are… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 24 CITATIONS

Efficient corpus selection for statistical machine translation

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Investigations on large-scale lightly-supervised training for statistical machine translation

VIEW 4 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Semi-supervised model adaptation for statistical machine translation

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Transductive learning for statistical machine translation

VIEW 3 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Empirical Use of Information Retrieval to Build Synthetic Data for SMT Domain Adaptation

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2016
VIEW 3 EXCERPTS
CITES RESULTS & METHODS

Similar Papers

Loading similar papers…