POS-based Word Reorderings for Statistical Machine Translation

@inproceedings{Popovic2006POSbasedWR,
  title={POS-based Word Reorderings for Statistical Machine Translation},
  author={Maja Popovic and Hermann Ney},
  booktitle={LREC},
  year={2006}
}
In this work we investigate new possibilities for improving the quality of statistical machine translation (SMT) by applying word reorderings of the source language sentences based on Part-of-Speech tags. Results are presented on the European Parliament corpus containing about 700k sentences and 15M running words. In order to investigate sparse training data scenarios, we also report results obtained on about 1% of the original corpus. The source languages are Spanish and English and target… CONTINUE READING

Tables, Results, and Topics from this paper.

Key Quantitative Results

  • For our best translation system, we achieve up to 2% relative reduction of WER and up to 7% relative increase of BLEU score.

Citations

Publications citing this paper.

FILTER CITATIONS BY YEAR

2006
2018

CITATION STATISTICS

  • 2 Highly Influenced Citations

  • Averaged 3 Citations per year over the last 3 years

Similar Papers

Loading similar papers…