Greedy Decoding for Statistical Machine Translation in Almost Linear Time

  title={Greedy Decoding for Statistical Machine Translation in Almost Linear Time},
  author={Ulrich Germann},
We present improvements to a greedy decoding algorithm for statistical machine translation that reduce its time complexity from at least cubic ( when applied naı̈vely) to practically linear time1 without sacrificing translation quality. We achieve this by integrating hypothesis evaluation into hypothesis creation, tiling improvements over the translation hypothesis at the end of each search iteration, and by imposing restrictions on the amount of word reordering during decoding. 
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 102 citations. REVIEW CITATIONS
65 Citations
14 References
Similar Papers


Publications citing this paper.

103 Citations

Citations per Year
Semantic Scholar estimates that this publication has 103 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 14 references

Language translation apparatus and method using context-based translation models

  • Berger, L. Adam, +8 authors L. Robert
  • United States Patent 5,510,981.
  • 1996
Highly Influential
5 Excerpts

The mathematics of statistical machine translation: Parameter estimation

  • Brown, F. Peter, +4 authors L. Robert
  • Computational Linguistics, 19(2):263–311.
  • 1993
Highly Influential
4 Excerpts

Word reordering and DP-based search in statistical machine translation

  • Tillmann, Christoph, Ney, Hermann.
  • In: Proceedings of the 18th COLING. Saarbrücken…
  • 2000

Similar Papers

Loading similar papers…