Experimental Results | In estimating phrase translation probability , we use accumulated HMM-based phrase pair posteriors |
Experimental Results | as their ‘soft’ frequencies and then the final translation probability is the relative frequency. |
Introduction | Using relative frequency as translation probability is a common practice to measure goodness of a phrase pair. |
Introduction | The translation probability can also be discriminatively trained such as in Tillmann and Zhang (2006). |
Using Translation Probability | More specifically, by using translation probabilities , we can rewrite equation (11) and (12) as follow: |
Using Translation Probability | From Table 6, we see that the performance of our approach can be further boosted by using translation probability . |
Using Translation Probability | Using Translation Probability 5 Related Work |