Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | Next revision Both sides next revision | ||
|
courses:rg:2012:encouraging-consistent-translation [2012/10/17 11:40] dusek |
courses:rg:2012:encouraging-consistent-translation [2012/10/17 11:43] dusek |
||
|---|---|---|---|
| Line 45: | Line 45: | ||
| * They define 3 features that are designed to be biased towrds consistency -- or are they? | * They define 3 features that are designed to be biased towrds consistency -- or are they? | ||
| * If e.g. two variants are used 2 times each, they will have roughly the same score | * If e.g. two variants are used 2 times each, they will have roughly the same score | ||
| - | | + | * The BM25 function is a refined version of the [[http:// |
| - | | + | |
| * The exact parameter values are probably not tuned, left at a default value (and maybe they don't have much influence anyway) | * The exact parameter values are probably not tuned, left at a default value (and maybe they don't have much influence anyway) | ||
| * See NPFL103 for details on Information retrieval, it's largely black magic | * See NPFL103 for details on Information retrieval, it's largely black magic | ||
| Line 56: | Line 55: | ||
| * The resulting weights are not mentioned, but if the weight is < 0, will this favor different translation choices? | * The resulting weights are not mentioned, but if the weight is < 0, will this favor different translation choices? | ||
| - | **Differences in features** | + | **Meaning of the individual |
| * C1 indicates that a certain Hiero rule was used frequently | * C1 indicates that a certain Hiero rule was used frequently | ||
| * but rules are very similar, so we also need something less fine-grained | * but rules are very similar, so we also need something less fine-grained | ||
| - | * C2 is a target-side feature, just counts the target side tokens | + | * C2 is a target-side feature, just counts the target side tokens |
| * It may be compared to Language Model features, but is trained only on the target part of the bilingual training data. | * It may be compared to Language Model features, but is trained only on the target part of the bilingual training data. | ||
| + | * C3 counts occurrences of source-target token pairs (and uses the "most important" | ||
| + | **Requirements of the new features** | ||
| + | * They need two passes through the data | ||
| + | * You need to have document segmentation | ||
| + | * Since the frequencies are trained on the training set, you can just translate one document at a time, no need to have full sets of documents | ||