Scoring and Optimization: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
| Line 17: | Line 17: | ||
in the corpus, resulting in <math>P(\mathbf{e}|\mathbf{f}) = P(\mathbf{f}|\mathbf{e}) | in the corpus, resulting in <math>P(\mathbf{e}|\mathbf{f}) = P(\mathbf{f}|\mathbf{e}) | ||
= 1</math>. Several methods exist for computing lexical weights. The most common one | = 1</math>. Several methods exist for computing lexical weights. The most common one | ||
is based on word alignment inside the phrase | is based on word alignment inside the phrase. The | ||
probability of each | probability of each ''foreign'' word <math>f_j</math> is estimated as the average of | ||
lexical translation probabilities <math>w(f_j, e_i)</math> over the English words aligned | lexical translation probabilities <math>w(f_j, e_i)</math> over the English words aligned | ||
to it. Thus for the phrase <math>(\mathbf{e},\mathbf{f})</math> with the set of alignment | to it. Thus for the phrase <math>(\mathbf{e},\mathbf{f})</math> with the set of alignment | ||
Revision as of 14:53, 24 August 2015
 | |
| Lecture video: |
web TODO Youtube |
|---|---|
{{#ev:youtube|https://www.youtube.com/watch?v=rDkZOINdPhw&index=11&list=PLpiLOsNLsfmbeH-b865BwfH15W0sat02V%7C800%7Ccenter}}
Features of MT Models
Phrase Translation Probabilities
Lexical Weights
Lexical weights are a method for smoothing the phrase table. Infrequent phrases have unreliable probability estimates; for instance many long phrases occur together only once in the corpus, resulting in . Several methods exist for computing lexical weights. The most common one is based on word alignment inside the phrase. The probability of each foreign word is estimated as the average of lexical translation probabilities over the English words aligned to it. Thus for the phrase with the set of alignment points , the lexical weight is:
