论文信息 - An Efficient A* Search Algorithm for Statistical Machine Translation

An Efficient A* Search Algorithm for Statistical Machine Translation

In this paper, we describe an efficient A* search algorithm for statistical machine translation. In contrary to beam-search or greedy approaches it is possible to guarantee the avoidance of search errors with A*. We develop various so-phisticated admissible and almost admissible heuristic functions. Especially our newly developped method to perform a multi-pass A* search with an iteratively improved heuristic function allows us to translate even long sentences. We compare the A* search algorithm with a beam-search approach on the Hansards task.

[1] Nils J. Nilsson,et al. Problem-solving methods in artificial intelligence , 1971, McGraw-Hill computer science series.

[2] Hermann Ney,et al. A Comparison of Alignment Models for Statistical Machine Translation , 2000, COLING.

[3] Christoph Tillmann,et al. Word re-ordering and dynamic programming based search algorithm for statistical machine translation , 2002 .

[4] W. W. Bledsoe,et al. Review of "Problem-Solving Methods in Artificial Intelligence by Nils J. Nilsson", McGraw-Hill Pub. , 1971, SGAR.

[5] David Yarowsky,et al. Statistical Machine Translation: Final Report , 1999 .

[6] Alexander H. Waibel,et al. Decoding Algorithm in Statistical Machine Translation , 1997, ACL.

[7] Hermann Ney,et al. Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation , 2003, CL.

[8] Robert L. Mercer,et al. The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[9] Hermann Ney,et al. Improved Statistical Alignment Models , 2000, ACL.

[10] Hermann Ney,et al. HMM-Based Word Alignment in Statistical Translation , 1996, COLING.

[11] Hermann Ney,et al. Word Re-ordering and DP-based Search in Statistical Machine Translation , 2000, COLING.