Combining decision trees and transformation-based learning to correct transferred linguistic representations

Simon Corston-Oliver, Michael Gamon


Abstract
We approach to correcting features in transferred linguistic representations in machine translation. The hybrid approach combines decision trees and transformation-based learning. Decision trees serve as a filter on the intractably large search space of possible interrelations among features. Transformation-based learning results in a simple set of ordered rules that can be compiled and executed after transfer and before sentence realization in the target language. We measure the reduction in noise in the linguistic representations and the results of human evaluations of end-to-end English-German machine translation.
Anthology ID:
2003.mtsummit-papers.8
Volume:
Proceedings of Machine Translation Summit IX: Papers
Month:
September 23-27
Year:
2003
Address:
New Orleans, USA
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2003.mtsummit-papers.8
DOI:
Bibkey:
Cite (ACL):
Simon Corston-Oliver and Michael Gamon. 2003. Combining decision trees and transformation-based learning to correct transferred linguistic representations. In Proceedings of Machine Translation Summit IX: Papers, New Orleans, USA.
Cite (Informal):
Combining decision trees and transformation-based learning to correct transferred linguistic representations (Corston-Oliver & Gamon, MTSummit 2003)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2003.mtsummit-papers.8.pdf