| J99-1003 | sentence boundaries . However | bitext mapping | at the sentence level is not |
| J99-1003 | units in their two halves . The | bitext mapping | problem can be formulated in |
| E97-1039 | SIMR the mostly widely applicable | bitext mapping | algorithm to date . SIMR opens |
| J99-1003 | advances the state of the art of | bitext mapping | by formulating the problem in |
| E97-1039 | map ( TBM ) . The purpose of a | bitext mapping | algorithm is to produce bitext |
| C96-2129 | handconstructed gold standard for evaluating | bitext mapping | algorithms . Quantitative evaluation |
| E97-1039 | thereafter , Church ( 1993 ) found that | bitext mapping | at the sentence level is not |
| E97-1039 | Injective Map Recognizer ( SIMR ) | bitext mapping | algorithm advances the state |
| J99-1003 | geometric interpretation of the | bitext mapping | problem and a discussion of previous |
| J99-1003 | optimize . The objective function for | bitext mapping | should measure the difference |
| E97-1039 | optimize . The objective function for | bitext mapping | should measure the difference |
| J99-1003 | them useless for the purposes of | bitext mapping | algorithms . Fortunately , only |
| E97-1039 | important information source for | bitext mapping | . It is likely that the accuracy |
| J99-1003 | point of view , the success of a | bitext mapping | algorithm hinges on three tasks |
| E97-1039 | are lower than those of other | bitext mapping | algorithms by an order of magni |
| E97-1039 | algorithm presented in this paper is a | bitext mapping | algorithm that advances the state |
| E97-1039 | halves of a bitext . The ideal | bitext mapping | algorithm should be fast and |
| C96-2129 | omission . Even with today 's poor | bitext mapping | technology , ADOMIT lit , ( Is |
| C96-2129 | that , even with today 's poor | bitext mapping | technology , ADOMIT is a valuable |
| E97-1039 | SIMR to find TPC chains . Other | bitext mapping | algorithms mitigate this source |
