| N04-1034 | The others are passed on to the | parallel sentence selection | stage . This step removes much |
| J05-4003 | The others are passed on to the | parallel sentence selection | stage . This step removes most |
| N04-1034 | most important feature of our | parallel sentence selection | approach is its robustness . |
| J05-4003 | most important feature of our | parallel sentence selection | approach is its robust - ness |
| N04-1034 | robustness of the system . 2.3 | Parallel sentence selection | For each candidate sentence pair |
| W09-3109 | then proceed by explaining our | parallel sentence selection | scheme and the post-processing |
| P09-2050 | As the first step , we employ | parallel sentence selection | , described in Sec . 3 , to remove |
| E09-1003 | then proceed by explaining our | parallel sentence selection | scheme and the post-processing |
| P09-2050 | approaches to address noisy data via | parallel sentence selection | , global - context based scoring |
| J05-4003 | so if a few of the content 2.3 | Parallel Sentence Selection | For each candidate sentence pair |
| P15-1069 | optimization using complex features for | parallel sentence selection | . In their experiments they use |
| P15-1069 | subsections . 3.1 Domain-Specific | Parallel Sentence Selection | In order to generate the best |
| P09-2050 | Holistic Solution We employ the | parallel sentence selection | as a pre-processing step , and |
