| E12-1016 | included results for a purely | random sentence selection | without replacement . In the |
| E12-1016 | neither compare their technique with | random sentence selection | , nor with a model trained with |
| P09-1021 | for 10 total iterations . The | random sentence selection | baselines are averaged over 3 |
| D15-1213 | notation . However , we observe that | random sentence selection | of the supervised sample results |
| P09-1021 | significant improvement compared to a | random sentence selection | baseline . We also provide new |
| X98-1026 | algorithm . We also implemented a | random sentence selection | algorithm as a baseline comparison |
| E12-1016 | significant improvements over | random sentence selection | but also an improvement over |
| W00-0403 | of MEAD Since the baseline of | random sentence selection | is already included in the evaluation |
| N09-1047 | languages , this methods outperforms | random sentence selection | . 4.2 Realistic Low Density Language |
| N09-1047 | utility score outperforms the strong | random sentence selection | baseline and other methods ( |
| N09-1047 | involves ran - domness , such as | random sentence selection | baseline and HAS , is averaged |
| N09-1047 | improvements in translation compared to a | random sentence selection | baseline , when test and training |
| P09-1021 | proposed methods outperform the | random sentence selection | baseline and GeomPhrase . We |
| P09-1021 | Fig. 3 shows the performance of | random sentence selection | for AL combined with self-training/co-training |
| P09-1021 | Spanish - English . In addition to | random sentence selection | baseline , we also compare the |
| W97-0704 | algorithm We also implemented a | random sentence selection | algorithm as a baseline comparison |
