Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
|
 |
Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System
| |
|
Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System
Chung-hye Han2  , Benoit Lavoie3 , Martha Palmer2 , Owen Rambow4 , Richard Kittredge3 , Tanya Korelsky3 , Nari Kim5 and Myunghee Kim3
| (2) |
Dept. of Computer and Information Sciences/IRCS, Univ. of Pennsylvania, PA 19104 Philadelphia, USA |
| (3) |
CoGenTex, Inc., NY 14850-1589 Ithaca, USA |
| (4) |
ATT Labs-Research, B233, Florham Park, NJ 07932, USA |
| (5) |
Konan Technology, Inc., Seoul 135-090, Korea |
Abstract
This paper describes an approach for handling structural divergences and recovering dropped arguments in an implemented Korean
to English machine translation system. The approach relies on canonical predicate-argument structures (or dependency structures),
which provide a suitable pivot representation for the handling of structural divergences and the recovery of dropped arguments.
It can also be converted to and from the interface representations of many off-the-shelf parsers and generators.
The work reported in this paper was supported by contract DAAD 17-99-C-0008 awarded by the Army Research Lab to CoGenTex,
Inc., with the University of Pennsylvania as a subcontractor and NSF Grant – VerbNet, IIS 98-00658. Owen Rambow’s contribution
to this paper was made when he was with CoGenTex, Inc. and Nari Kim’s contribution was made when she was a visiting researcher
at IRCS, UPenn.
Fulltext Preview (Small, Large)
 References secured to subscribers.
|
|
|
|
|
|