Translation combination using factored word substitution (2009)
| Venue: | In Proceedings of the Fourth Workshop on Statistical Machine Translation |
| Citations: | 1 - 0 self |
BibTeX
@INPROCEEDINGS{Federmann09translationcombination,
author = {Christian Federmann and Silke Theison and Andreas Eisele and Hans Uszkoreit and Yu Chen and Michael Jellinghaus and Sabine Hunsicker},
title = {Translation combination using factored word substitution},
booktitle = {In Proceedings of the Fourth Workshop on Statistical Machine Translation},
year = {2009}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We present a word substitution approach to combine the output of different machine translation systems. Using part of speech information, candidate words are determined among possible translation options, which in turn are estimated through a precomputed word alignment. Automatic substitution is guided by several decision factors, including part of speech, local context, and language model probabilities. The combination of these factors is defined after careful manual analysis of their respective impact. The approach is tested for the language pair German-English, however the general technique itself is language independent. 1
Citations
| 805 | A systematic comparison of various statistical alignment models - Och, Ney - 2003 |
| 412 | Probabilistic part-of-speech tagging using decision trees - Schmid - 1994 |
| 30 | Statistical machine translation - Lopez |
| 13 | Statistical Post-Editing on SYSTRAN’s Rule-Based Translation System - Dugast, Senellart, et al. - 2007 |
| 7 | Combining outputs from multiple machine translation systems - 2007a |
| 1 | Improved word-level system combination for machine translation - 2007b |
