Scoring and Optimization

Lecture 13: Scoring and Optimization

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

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 $P(\mathbf {e} |\mathbf {f} )=P(\mathbf {f} |\mathbf {e} )=1$. Several methods exist for computing lexical weights. The most common one is based on word alignment inside the phrase \citep{koehn:phd-thesis}. The probability of each \emph{foreign} word $f_{j}$ is estimated as the average of lexical translation probabilities $w(f_{j},e_{i})$ over the English words aligned to it. Thus for the phrase $(\mathbf {e} ,\mathbf {f} )$ with the set of alignment points $a$, the lexical weight is:

${\text{lex}}(\mathbf {f} |\mathbf {e} ,a)=\prod _{j=1}^{l_{f}}{\frac {1}{|{i|(i,j)\in a}|}}\sum _{\forall (i,j)\in a}w(f_{j},e_{i})$