Content deleted Content added
m →Model 2: added formatting |
|||
Line 20:
The IBM Model 2 has an additional model for alignment that is not present in Model 1. For example, using only IBM Model 1 the translation probabilities for these translations would be the same:
[[File:IBM models 01.jpg|none]]
The IBM Model 2 addressed this issue by modeling the translation of a foreign input word in position <math>i</math> to a native language word in position <math>j</math> using an alignment probability distribution defined as:
:<math>a(i\lor j,l_e,l_f)</math>
| |||