Exploring Different Representational Units in English-to-Turkish Statistical Machine Translation

@inproceedings{Oflazer2007ExploringDR,
  title={Exploring Different Representational Units in English-to-Turkish Statistical Machine Translation},
  author={Kemal Oflazer and Ilknur Durgar El-Kahlout},
  booktitle={WMT@ACL},
  year={2007}
}
We investigate different representational granularities for sub-lexical representation in statistical machine translation work from English to Turkish. We find that (i) representing both Turkish and English at the morpheme-level but with some selective morpheme-grouping on the Turkish side of the training data, (ii) augmenting the training data with "sentences" comprising only the content words of the original training data to bias root word alignment, (iii) reranking the n-best morpheme… CONTINUE READING

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

Key Quantitative Results

  • Despite our very limited training data, we improve from 20.22 BLEU points for our simplest model to 25.08 BLEU points for an improvement of 4.86 points or 24% relative.

Citations

Publications citing this paper.
SHOWING 1-10 OF 69 CITATIONS

Statistical Post-Editing for a Statistical MT System

VIEW 13 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Using morphology in English-Turkish statistical machine translation

  • 2012 20th Signal Processing and Communications Applications Conference (SIU)
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENCED

Automatic post-editing of phrase-based machine translation outputs

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Limsi @ Iwslt 2010

VIEW 9 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2007
2018

CITATION STATISTICS

  • 9 Highly Influenced Citations

Similar Papers

Loading similar papers…