Fast decoding and optimal decoding for machine translation
Ulrich Germann, Michael Jahr, Kevin K. Knight et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 2001
A good decoding algorithm is critical to the success of any statistical machine translation system. The decoder's job is to find the translation that is most likely according to set of previously learned parameters (and a formula for combining them). Since the space of possible translations is extremely large, typical decoding algorithms are only able to examine a portion of it, thus risking to miss good solutions. In this paper, we compare the speed and output quality of a traditional stack-based decoding algorithm with two new decoders: a fast greedy decoder and a slow but optimal decoder that treats decoding as an integer-programming optimization problem.
Cited by 235 works. doi:10.3115/1073012.1073042 Open-access PDF
Authors
References
- Computers and Intractability: A Guide to the Theory of NP-Completeness
- The mathematics of statistical machine translation: parameter estimation
- Fast Sequential Decoding Algorithm Using a Stack
- A new method for solving hard satisfiability problems
- Determining computational complexity from characteristic ‘phase transitions’
- A polynomial-time algorithm for statistical machine translation
- A DP based search using monotone alignments in statistical translation
- Decoding complexity in word-replacement translation models
- Decoding algorithm in statistical machine translation
- A DP based search using monotone alignments in statistical translation