Abstract | ||
---|---|---|
This paper presents a maximum entropy word alignment algorithm for Arabic-English based on supervised training data. We demonstrate that it is feasible to create training material for problems in machine translation and that a mixture of supervised and unsupervised methods yields superior performance. The probabilistic model used in the alignment directly models the link decisions. Significant improvement over traditional word alignment techniques is shown as well as improvement on several machine translation tests. Performance of the algorithm is contrasted with human annotation performance. |
Year | DOI | Venue |
---|---|---|
2005 | 10.3115/1220575.1220587 | HLT/EMNLP |
Keywords | Field | DocType |
maximum entropy word aligner,link decision,arabic-english machine translation,maximum entropy word alignment,training material,human annotation performance,traditional word alignment technique,machine translation,machine translation test,significant improvement,supervised training data,superior performance,probabilistic model,maximum entropy | Rule-based machine translation,Annotation,Arabic,Computer science,Word error rate,Machine translation,Speech recognition,Statistical model,Artificial intelligence,Supervised training,Natural language processing,Principle of maximum entropy | Conference |
Volume | Citations | PageRank |
H05-1 | 55 | 2.77 |
References | Authors | |
13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abraham Ittycheriah | 1 | 534 | 61.23 |
Salim Roukos | 2 | 6248 | 845.50 |