| P06-1103 | than two languages . Pair-wise | time sequence scoring | and transliteration models should |
| N06-1011 | than two languages . Pairwise | time sequence scoring | and transliteration models should |
| P06-1103 | effectively rely on the quality of | time sequence scoring | , we used a simple , knowledge |
| P06-1103 | iterations . 4.3 Comparison of | time sequence scoring | functions We compared the performance |
| N06-1011 | transliteration in the first iteration . | Time sequence scoring | function chooses it to be one |
| P06-1103 | candidates in another language . | Time sequence scoring | is then used to rerank the list |
| P06-1103 | transliteration in the first iteration . | Time sequence scoring | function chooses it to be one |
