Domain Adaptation for Statistical Machine Translation with Monolingual Resources

@inproceedings{Bertoldi2009DomainAF,
  title={Domain Adaptation for Statistical Machine Translation with Monolingual Resources},
  author={Nicola Bertoldi and Marcello Federico},
  booktitle={WMT@EACL},
  year={2009}
}
Domain adaptation has recently gained interest in statistical machine translation to cope with the performance drop observed when testing conditions deviate from training conditions. The basic idea is that in-domain training data can be exploited to adapt all components of an already developed system. Previous work showed small performance gains by adapting from limited in-domain bilingual data. Here, we aim instead at significant performance gains by exploiting large but cheap monolingual in… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Finally, we described how to reduce the time for training models from a synthetic corpus generated through Moses by 50% at least, by exploiting word-alignment information provided during decoding.

Citations

Publications citing this paper.
SHOWING 1-10 OF 115 CITATIONS

Semi-Supervised Neural Machine Translation via Marginal Distribution Estimation

Yijun Wang, Yingce Xia, +4 authors Tie-Yan Liu
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2019
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Twitter Translation using Translation-Based Cross-Lingual Retrieval

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Machine Translation for Twitter

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A survey of domain adaptation for statistical machine translation

  • Machine Translation
  • 2017
VIEW 4 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

LEVERAGING DIVERSE SOURCES IN STATISTICAL MACHINE TRANSLATION

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 9 Highly Influenced Citations

  • Averaged 9 Citations per year from 2017 through 2019