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 14:56] dusek |
courses:rg:2012:encouraging-consistent-translation [2012/10/16 15:15] dusek |
||
---|---|---|---|
Line 8: | Line 8: | ||
The list of discussed topics follows the outline of the paper: | The list of discussed topics follows the outline of the paper: | ||
==== Sec. 2. Related Work ==== | ==== Sec. 2. Related Work ==== | ||
- | | + | |
- | * Yes: the decoder just gets additional features, but the decision is up to it -- Carpuat 2009 just post-edits the outputs and substitutes the most likely variant everywhere | + | **Differences |
- | * Using Carpuat 2009's approach directly in the decoder would influence neighboring words through LM, so even using this in the decoder and not as post-editing leads to a different outcome | + | * It is different: the decoder just gets additional features, but the decision is up to it -- Carpuat 2009 just post-edits the outputs and substitutes the most likely variant everywhere |
- | * //Human translators and one sense per discourse// | + | * Using Carpuat 2009's approach directly in the decoder would influence neighboring words through LM, so even using this in the decoder and not as post-editing leads to a different outcome |
- | * This suggests that modelling human translators is the same as modelling one sense per discourse -- this is suspicious | + | |
- | * The authors do not state their evidence clearly. | + | **Human translators and one sense per discourse** |
- | * One sense is not the same as one translation | + | * This suggests that modelling human translators is the same as modelling one sense per discourse -- this is suspicious |
+ | * The authors do not state their evidence clearly. | ||
+ | * One sense is not the same as one translation | ||
==== Sec. 3. Exploratory analysis ==== | ==== Sec. 3. Exploratory analysis ==== | ||
+ | |||
+ | **Hiero** | ||
+ | * The idea would most probably work the same in normal phrase-based SMT, but the authors use hierarchical phrase-based translation (Hiero) | ||
+ | * Hiero is summarized in Fig. 1: the phrases may contain non-terminals ('' | ||
+ | * The authors chose the '' | ||
+ | * The choice was probably arbitrary, other systems would yield similar results | ||
+ | |||
+ | **Forced decoding** | ||
+ | * This means that the decoder is given source //and// target sentence and has to provide the rules/ | ||
+ | * The decoder might be unable to find the appropriate rules (for unseen words) | ||
+ | * It is a different decoder mode, for which it must be adjusted | ||
+ | * 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 // |