Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation

@inproceedings{Ma2009BilinguallyMD,
  title={Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation},
  author={Yanjun Ma and Andy Way},
  booktitle={EACL},
  year={2009}
}
We introduce a word segmentation approach to languages where word boundaries are not orthographically marked, with application to Phrase-Based Statistical Machine Translation (PB-SMT). Instead of using manually segmented monolingual domain-specific corpora to train segmenters, we make use of bilingual corpora and statistical word alignment techniques. First of all, our approach is adapted for the specific translation task at hand by taking the corresponding source (target) language into account… CONTINUE READING
Highly Cited
This paper has 65 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 27 extracted citations

66 Citations

051015'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 66 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.