[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » courses » rg » 2012 » encouraging-consistent-translation-bushra

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
courses:rg:2012:encouraging-consistent-translation-bushra [2012/10/23 20:14]
popel typos and 1 comment 		courses:rg:2012:encouraging-consistent-translation-bushra [2012/10/29 20:30] (current)
jawaid
Line 19: Line 19:
     - C<sub>3</sub> goes over all alignment pairs and for each rule it selects those term pairs that have maximum feature value.     - C<sub>3</sub> goes over all alignment pairs and for each rule it selects those term pairs that have maximum feature value.
  
-Evaluation:+====Evaluation:====
  
   - Cdec's implementation of Hierarchical MT is used in this work. As we know, hierarchical decoding is also implemented in other MT systems such as Moses, Joshua etc. The selection of cdec over other MT systems is authors' personal choice and doest not bring extra benefits.   - Cdec's implementation of Hierarchical MT is used in this work. As we know, hierarchical decoding is also implemented in other MT systems such as Moses, Joshua etc. The selection of cdec over other MT systems is authors' personal choice and doest not bring extra benefits.
Line 33: Line 33:
 ====Conclusion:==== ====Conclusion:====
 Paper is nicely written and all experiments are well documented. We believe that consistent translation choices system is well suited only for translating from direction of morphologically-rich to morphologically-low language pairs and not the other way round. For translating in direction of morphologically rich languages, this approach can make serious errors by putting different morphological forms of the words, bearing different meanings, under the consistent translations. Paper is nicely written and all experiments are well documented. We believe that consistent translation choices system is well suited only for translating from direction of morphologically-rich to morphologically-low language pairs and not the other way round. For translating in direction of morphologically rich languages, this approach can make serious errors by putting different morphological forms of the words, bearing different meanings, under the consistent translations.
- 

[ Back to the navigation ] [ Back to the content ]