The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Decoding complexity in word-replacement translation models
Computational Linguistics
Decoding algorithm in statistical machine translation
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Fast and optimal decoding for machine translation
Artificial Intelligence
Word re-ordering and DP-based search in statistical machine translation
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Greedy decoding for statistical machine translation in almost linear time
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
An efficient A* search algorithm for statistical machine translation
DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
An english-hindi statistical machine translation system
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
Theory of alignment generators and applications to statistical machine translation
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Hi-index | 0.00 |
The decoding problem in Statistical Machine Translation (SMT) is a computationally hard combinatorial optimization problem. In this paper, we propose a new algorithmic framework for solving the decoding problem and demonstrate its utility. In the new algorithmic framework, the decoding problem can be solved both exactly and approximately. The key idea behind the framework is the modeling of the decoding problem as one that involves alternating maximization of two relatively simpler subproblems. We show how the subproblems can be solved efficiently and how their solutions can be combined to arrive at a solution for the decoding problem. A family of provably fast decoding algorithms can be derived from the basic techniques underlying the framework and we present a few illustrations. Our first algorithm is a provably linear time search algorithm. We use this algorithm as a subroutine in the other algorithms. We believe that decoding algorithms derived from our framework can be of practical significance.