| W08-0401 | category . Next , we conducted | J-E translation | experiments using the same corpus |
| P91-1024 | important and complicated problem in | J-E translation | . In contrast with the preceding |
| P11-2076 | dl = − 1 ) was 1.20 % in | J-E translation | and 1.41 % in E-J translation |
| C94-1007 | with 825 Japanese sentences for | J-E translation | and 607 English sentences fl |
| P11-2076 | without a context document . For | J-E translation | , we converted the dependency |
| W03-1109 | 1999 ) have used word-by-word | J-E translations | in their study on interactive |
| P11-2076 | improvement of 1.20 % BLEU points for | J-E translation | and 1.41 % BLEU points for E-J |
| P91-1024 | not exhaustive ) of phenomena in | J-E translation | that are suitable for EBMT : |
| W12-4213 | Resolution can Improve the Quality of | J-E Translation | </title> Hirotoshi Taira Katsuhito |
| C94-1007 | vocabulary of 1500 words . In | J-E translation | , the system on a Lisp machine |
