Stanford InfoLab Publication Server

Multistack Decoding in Statistical Machine Translation

Jahr, Michael E. (2001) Multistack Decoding in Statistical Machine Translation. Technical Report. Stanford.




In a machine translation system, decoding is the process of finding the most likely translation according to previously learned parameters. The success of any such system is highly dependent on the quality of its decoder. Stack decoders were the first decoders developed for statistical machine translation, and they represent a good compromise between search thoroughness and efficiency. In this thesis I review the models used in IBM's Candide system, and then describe a multistack decoder developed for use with the models. I also compare the performance of the multistack decoder to that of two other decoding algorithms.

Item Type:Techreport (Technical Report)
Uncontrolled Keywords:machine translation, statistical methods, stack decoding, search
Subjects:Computer Science
Related URLs:Project Homepage
ID Code:524
Deposited By:Import Account
Deposited On:01 Oct 2002 17:00
Last Modified:27 Dec 2008 10:03

Download statistics

Repository Staff Only: item control page