Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
courses:rg:2012:encouraging-consistent-translation [2012/10/16 15:07] dusek |
courses:rg:2012:encouraging-consistent-translation [2012/10/17 11:43] dusek |
||
---|---|---|---|
Line 24: | Line 24: | ||
* The authors chose the '' | * The authors chose the '' | ||
* The choice was probably arbitrary, other systems would yield similar results | * The choice was probably arbitrary, other systems would yield similar results | ||
+ | |||
**Forced decoding** | **Forced decoding** | ||
* This means that the decoder is given source //and// target sentence and has to provide the rules/ | * This means that the decoder is given source //and// target sentence and has to provide the rules/ | ||
Line 30: | Line 31: | ||
* Forced decoding is much more informative for Hiero translations than for " | * Forced decoding is much more informative for Hiero translations than for " | ||
+ | **The choice and filtering of " | ||
+ | * The " | ||
+ | * Table 1 is unfiltered -- only some of the " | ||
+ | * Cases that are //too similar// (less than 1/2 characters differ) are //joined together// | ||
+ | * Beware, this notion of grouping is not well-defined, | ||
+ | * Cases where //only one translation variant prevails// are // | ||
+ | |||
+ | ==== Sec. 4. Approach ==== | ||
+ | The actual experiments begin only now; the used data is different. | ||
+ | |||
+ | **Choice of features** | ||
+ | * 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 | ||
+ | * 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) | ||
+ | * See NPFL103 for details on Information retrieval, it's largely black magic | ||
+ | |||
+ | **Feature weights** | ||
+ | * The usual model in MT is scoring the hypotheses according to the feature values ('' | ||
+ | * '' | ||
+ | * The feature weights are trained on a heldout data set using [[http:// | ||
+ | * The resulting weights are not mentioned, but if the weight is < 0, will this favor different translation choices? | ||
+ | |||
+ | **Meaning of the individual features** | ||
+ | * C1 indicates that a certain Hiero rule was used frequently | ||
+ | * 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 (only the "most important" | ||
+ | * 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 |