D13-1163 measure the cohesion of the target document translation . The basic idea is to reward
D13-1163 lexical cohesion devices are used in document translation . As lexical chains capture lexical
C82-1057 . There is a large demand for document translation in Japan . The fifth generation
H01-1060 IN - DEXING We have adopted a document translation architecture for two rea - sons
J03-3002 of identifying English - French document translations . 3.1 Quantifying Translational
C04-1138 successful for the task of identifying document translations . This approach should thus also
D15-1012 documents . This is also known as the document translation scheme . • CoRank : We
H01-1041 plan to expand the module for document translations . 5 . ACKNOWLEDGMENTS We would
H01-1060 of two main com - ponents : 1 . Document translation and indexing 2 . Interactive
E12-1012 groups of approaches to CLIR : document translation and query translation . We concentrate
D14-1064 translation approaches and ( ii ) document translation . While the exact same problem
H01-1060 be a concern ) . Sec - ond , a document translation architecture simplifies the display
H01-1033 experiments , we use top2 balanced document translation , in which we produce exactly
D15-1106 when applied to a Chinese-English document translation reranking task . 2 Related work
D13-1153 approach does not require whole document translations , but relies on the same simple
J11-3005 cross-lingual text categorization : document translation , terminology translation , and
D13-1163 Generation Since a faithful target document translation should follow the same cohesion
A97-1024 a company that has to pay for document translation on a per word basis , every repeti
A00-1003 translation technology . Unlike document translation , there is no need to match every
D13-1163 to constrain word selection for document translation so that the generated document
hide detail