| Abstract | Build the baseline system , estimate { 0, k }. |
| Abstract | the baseline system , compute BLE U (En, El). |
| Abstract | Other models used in the baseline system include lexicalized ordering model, word count and phrase count, and a 3-gram LM trained on the English side of the parallel training corpus. |
| Evaluation | First, we compare our system to baseline systems . |
| Evaluation | 4.1 Comparison to Baseline Systems |
| Evaluation | Table 5: Comparison to baseline systems |
| Experimental Design | 5Since the addition of these features, essentially incurs reranking, it follows that the systems would exhibit the exact same performance as the baseline system with l—best lists. |
| Introduction | The performance of this baseline system could be potentially further improved using discriminative reranking (Collins, 2000). |
| Introduction | baseline system . |
| Experiments | We found that adding word classes improved alignment quality a little, but more so for the baseline system (see Table 3). |
| Experiments | Table 3: Adding word classes improves the F-score in both directions for Arabic-English alignment by a little, for the baseline system more so than ours. |
| Experiments | In particular, the baseline system demonstrates typical “garbage collection” behavior (Moore, 2004) in all four examples. |
| Experiments | 5.3.1 Baseline System |
| Experiments | We use a BTG phrase-based system with a Max-Ent based leXicalized reordering model (Wu, 1997; Xiong et al., 2006) as our baseline system for |
| Experiments | From Table 2, we can see our ranking reordering model significantly improves the performance for both English-to-Japanese and Japanese-to-English experiments over the BTG baseline system . |