Article

Generation-Heavy Hybrid Machine Translation

08/2002;
Source: CiteSeer

ABSTRACT This paper describes GenerationHeavy Hybrid Machine Translation (GHMT), a novel approach for trans- lating between structurally-divergent language pairs with asymmetrical resources. The approach depends on the existence of rich target language resources such as word lexical semantics, categorial variations and subcategorization frames. These resources are used to overgenerate multiple lexico-structural variations from a target-glossed syntactic dependency representation of the source language sentence. This symbolic overgeneration, which accounts for a wide range of possible variations, is constrained by a statistical targetlanguage model. The exploitation of target language resources (symbolic and statistical) to handle a problem usually reserved for Transfer and Interlingual MT is useful for translation from source languages with scarce linguistic resources. A preliminary evaluation on the application of this approach to Spanish-English MT is conducted with promising results.

0 0
 · 
0 Bookmarks
 · 
38 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Full-text

View
0 Downloads
Available from

Keywords

asymmetrical resources
 
categorial variations
 
GenerationHeavy Hybrid Machine Translation
 
Interlingual MT
 
overgenerate multiple lexico-structural variations
 
possible variations
 
preliminary evaluation
 
promising results
 
resources
 
rich target language resources
 
scarce linguistic resources
 
source language sentence
 
source languages
 
statistical targetlanguage model
 
structurally-divergent language pairs
 
subcategorization frames
 
target language resources
 
target-glossed syntactic dependency representation
 
wide range
 
word lexical semantics