Sciweavers

Share
NAACL
2003

Greedy Decoding for Statistical Machine Translation in Almost Linear Time

8 years 11 months ago
Greedy Decoding for Statistical Machine Translation in Almost Linear Time
We present improvements to a greedy decoding algorithm for statistical machine translation that reduce its time complexity from at least cubic (  ¢¡¤£¦¥¨§ when applied na¨ıvely) 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.
Ulrich Germann
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where NAACL
Authors Ulrich Germann
Comments (0)
books