Lattice rescoring methods for statistical machine translation

@inproceedings{Blackwood2010LatticeRM,
  title={Lattice rescoring methods for statistical machine translation},
  author={Graeme W. Blackwood},
  year={2010}
}
Modern statistical machine translation (SMT) systems incl ude multiple interrelated components, statistical models, and processes. Translation is often facto red as a cascaded series of modules such that the output of one module serves as the input to the next; this i s the SMT pipeline. Simplifying assumptions, limited training data, and pruning during search mea n th t the hypothesis produced by a typical SMT decoder may not represent the best translation. Since an y rrors will be propagated… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 113 references

Statistical Machine Translation

View 13 Excerpts
Highly Influenced

Speech recognition with weighted finite-state transducers

M. Mohri, F. Pereira, M. Riley
Handbook on Speech Processing and Speech Communication. • 2008
View 10 Excerpts
Highly Influenced

A weighted finite state transducer translation template model for statistical machine translation

S H A N K A R K U M A R, Y O N G G A N G D E N G And W I L L I A M B Y R N E
2004
View 5 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…