Morphology-Aware Statistical Machine Translation Based on Morphs Induced in an Unsupervised Manner

@inproceedings{Virpioja2007MorphologyAwareSM,
  title={Morphology-Aware Statistical Machine Translation Based on Morphs Induced in an Unsupervised Manner},
  author={Sami Virpioja and Jaakko J. V{\"a}yrynen and Mathias Creutz and Markus Sadeniemi},
  year={2007}
}
In this paper, we apply a method of unsupervised morphology l earning to a state-of-the-art phrase-based statistical ma chine translation (SMT) system. In SMT, words are traditionally used as the sma llest units of translation. Such a system generalizes poorl y t word forms that do not occur in the training data. In particular, this is problematic for languages that are highly compounding, hig hly inflecting, or both. An alternative way is to use sub-word units, such as mor phemes. We use the… CONTINUE READING
Highly Cited
This paper has 103 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 77 extracted citations

103 Citations

01020'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 103 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 26 references

Similar Papers

Loading similar papers…